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

    Neuronpedia

    INDEX
    Explanations

    like

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _xor
    -0.07
     período
    -0.06
    数
    -0.06
     randomness
    -0.06
     today
    -0.06
    _prob
    -0.06
    罚
    -0.06
     verdad
    -0.06
    ової
    -0.06
     spect
    -0.06
    POSITIVE LOGITS
    Where
    0.07
    .Dep
    0.07
     거래
    0.06
    -dess
    0.06
    卫
    0.06
    ":
↵
    0.06
    들에게
    0.06
     seeing
    0.06
    English
    0.06
    ARCH
    0.06
    Act Density 0.010%

    No Known Activations