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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    holds
    -0.07
     obras
    -0.07
    _quantity
    -0.07
    ufac
    -0.06
     logistical
    -0.06
    なんて
    -0.06
    buster
    -0.06
     constitutes
    -0.06
     ноч
    -0.06
     리
    -0.06
    POSITIVE LOGITS
     آموزش
    0.07
     ایست
    0.07
    ften
    0.06
     Murdoch
    0.06
    ｊ
    0.06
     ह
    0.06
     알
    0.06
     besie
    0.06
    ToOne
    0.06
    .Report
    0.06
    Act Density 0.000%

    No Known Activations