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

    Neuronpedia

    INDEX
    Explanations

    name

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     LICENSE
    -0.07
     leg
    -0.07
    ermen
    -0.07
    在意
    -0.07
    ator
    -0.07
    LER
    -0.07
    力
    -0.07
    .LEADING
    -0.07
    endi
    -0.06
    RITE
    -0.06
    POSITIVE LOGITS
    ào
    0.07
    unn
    0.07
     więks
    0.07
    皇宫
    0.06
    大海
    0.06
    ㅁ
    0.06
    =mysqli
    0.06
    educ
    0.06
    -paper
    0.06
     incorporation
    0.06
    Act Density 0.001%

    No Known Activations