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

    Neuronpedia

    INDEX
    Explanations

    Managing expectations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    になった
    -0.08
     violence
    -0.07
     갖
    -0.07
    参加
    -0.06
     Gl
    -0.06
     noci
    -0.06
     acquisition
    -0.06
     voksne
    -0.06
     prosecution
    -0.06
     bartender
    -0.06
    POSITIVE LOGITS
    _ANY
    0.07
    _false
    0.07
     Alexa
    0.06
    .Volume
    0.06
    (?
    0.06
    (Search
    0.06
     editar
    0.06
    _begin
    0.06
     UserID
    0.06
    -click
    0.06
    Act Density 0.044%

    No Known Activations