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

    Neuronpedia

    INDEX
    Explanations

    year

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    addElement
    -0.07
    (flow
    -0.07
     wann
    -0.07
    _pedido
    -0.07
    (rawValue
    -0.06
    forc
    -0.06
     whitelist
    -0.06
     해야
    -0.06
     destined
    -0.06
    GORITH
    -0.06
    POSITIVE LOGITS
     keywords
    0.07
    ár
    0.06
     dumps
    0.06
    根
    0.06
     PL
    0.06
    ーク
    0.06
     кор
    0.06
    .private
    0.06
     stumble
    0.06
     Nẵng
    0.06
    Act Density 0.014%

    No Known Activations