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

    Neuronpedia

    INDEX
    Explanations

    question

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     blows
    -0.08
     politicians
    -0.07
    Histor
    -0.07
     Steve
    -0.07
    <Vertex
    -0.07
     counters
    -0.07
    计较
    -0.07
     analytic
    -0.07
     personnel
    -0.07
     sticks
    -0.07
    POSITIVE LOGITS
    idar
    0.07
    דעה
    0.07
    鳡
    0.07
    ꪕ
    0.07
    .ListBox
    0.06
    optgroup
    0.06
    퉜
    0.06
    .BatchNorm
    0.06
    handled
    0.06
    endas
    0.06
    Act Density 0.019%

    No Known Activations