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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating positive or negative evaluations

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

    not good

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     eût
    -0.54
    ViewFeatures
    -0.52
    期刊论文
    -0.49
     consultez
    -0.44
     betrekking
    -0.44
    meanor
    -0.42
    StructEnd
    -0.41
    UnknownFieldSet
    -0.40
     įsi
    -0.40
     achtergrond
    -0.40
    POSITIVE LOGITS
     GOOD
    0.60
    GOOD
    0.49
    хоро
    0.48
    FailureListener
    0.48
    tagHelperRunner
    0.48
    Good
    0.46
     SafeMath
    0.45
     good
    0.45
    BaseActivity
    0.45
    good
    0.45
    Act Density 0.005%

    No Known Activations