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

    Neuronpedia

    INDEX
    Explanations

    Information/Lists

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     三
    -0.07
    _setopt
    -0.06
     Virt
    -0.06
     Pra
    -0.06
    pecified
    -0.06
     opposes
    -0.06
     dign
    -0.06
     spe
    -0.06
     взрос
    -0.06
     кня
    -0.06
    POSITIVE LOGITS
    _hi
    0.07
    enheim
    0.07
    .cls
    0.07
     didn
    0.06
     may
    0.06
    CAN
    0.06
     don
    0.06
    ']+
    0.06
    idas
    0.06
    onen
    0.06
    Act Density 0.073%

    No Known Activations