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

    Neuronpedia

    INDEX
    Explanations

    academic references and citations

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

    number followed by size

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.33
    rrggbb
    -0.33
    inSlope
    -0.32
    آخر
    -0.28
     malo
    -0.28
    ⓧ
    -0.27
    principalColumn
    -0.27
    RefNanny
    -0.27
     aç
    -0.27
     refleja
    -0.27
    POSITIVE LOGITS
    MessageOf
    0.60
     itſelf
    0.56
     témoig
    0.56
    __]
    0.56
     ſta
    0.54
     ſever
    0.54
    InputBorder
    0.54
    OneToOne
    0.54
     Inſ
    0.54
     obſ
    0.53
    Act Density 0.339%

    No Known Activations