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

    Neuronpedia

    INDEX
    Explanations

    Code/technical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Publishing
    -0.07
    assessment
    -0.07
    ifferences
    -0.06
    讯
    -0.06
    Sortable
    -0.06
    ประโย
    -0.06
    ideo
    -0.06
     Emerson
    -0.06
     indifference
    -0.06
     proclaim
    -0.06
    POSITIVE LOGITS
    애
    0.06
     minecraft
    0.06
    ชน
    0.06
    ́t
    0.06
     vyb
    0.06
    DY
    0.06
    zas
    0.06
    fft
    0.06
    age
    0.06
     představ
    0.06
    Act Density 0.000%

    No Known Activations