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

    Neuronpedia

    INDEX
    Explanations

    problem

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cottage
    -0.08
     overrun
    -0.07
    _coupon
    -0.07
    뵘
    -0.07
     --------
    -0.06
    ⼦
    -0.06
    .logo
    -0.06
    𬙋
    -0.06
    .tooltip
    -0.06
     Elliott
    -0.06
    POSITIVE LOGITS
     problems
    0.11
    问题
    0.08
    Глав
    0.07
    rparr
    0.07
    상
    0.07
     Как
    0.07
    럴
    0.07
    BLEM
    0.06
     bệnh
    0.06
     The
    0.06
    Act Density 0.054%

    No Known Activations