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

    Neuronpedia

    INDEX
    Explanations

    code documentation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Essence
    -0.06
     braking
    -0.06
     hours
    -0.06
    icone
    -0.06
     k
    -0.06
    条
    -0.06
     entend
    -0.06
     nă
    -0.06
    录
    -0.06
    συ
    -0.06
    POSITIVE LOGITS
    ्पष
    0.07
    //↵
    0.07
     Equals
    0.07
    ynchron
    0.06
    miss
    0.06
    prech
    0.06
    침
    0.06
    收
    0.06
     irresponsible
    0.06
    SCII
    0.06
    Act Density 0.275%

    No Known Activations