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

    Neuronpedia

    INDEX
    Explanations

    legal terms/disclaimers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    worth
    -0.09
    boom
    -0.09
    Boom
    -0.08
    tsch
    -0.08
    bracht
    -0.08
    _record
    -0.08
     Dunk
    -0.08
    оснаб
    -0.08
    akit
    -0.08
    akas
    -0.08
    POSITIVE LOGITS
     возможность
    0.09
     випад
    0.09
     \(
    0.08
     modific
    0.08
     द
    0.08
     случаи
    0.08
    하면서
    0.08
     દ
    0.08
     możliwość
    0.08
     contrôle
    0.08
    Act Density 0.006%

    No Known Activations