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

    Neuronpedia

    INDEX
    Explanations

    b

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    EEE
    -0.07
    刚好
    -0.07
     غ
    -0.06
    환
    -0.06
     cst
    -0.06
    Cors
    -0.06
    颦
    -0.06
    .BL
    -0.06
    tensor
    -0.06
    申花
    -0.06
    POSITIVE LOGITS
    ทำการ
    0.08
    abcdef
    0.07
    UILabel
    0.07
     unwitting
    0.07
     подроб
    0.07
    一回事
    0.07
    ewriter
    0.07
    इ
    0.07
    sockopt
    0.07
    .ci
    0.07
    Act Density 0.002%

    No Known Activations