Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    words and phrases that express necessity or significance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Comes before citations or references

    np_acts-logits-general · gemini-2.0-flash

    unavoidable during, equivalent, act solely

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Pick
    -0.42
    AntiForgeryToken
    -0.41
    AlterField
    -0.38
    rosoft
    -0.38
     PROGRESS
    -0.37
     everyone
    -0.37
    Pick
    -0.36
    .*")]
    -0.36
    "}";
    -0.36
     chắc
    -0.35
    POSITIVE LOGITS
     kasarigan
    0.75
    SequentialGroup
    0.68
    RTCK
    0.52
    Basta
    0.50
     kadang
    0.47
    addGap
    0.46
     sometimes
    0.46
    或
    0.45
     Basta
    0.45
    +#+#
    0.45
    Act Density 0.652%

    No Known Activations