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

    Neuronpedia

    INDEX
    Explanations

    Software instructions/settings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Predicate
    -0.09
    预测软件
    -0.08
     Microsoft
    -0.08
    akr
    -0.08
    Microsoft
    -0.08
     Predicate
    -0.08
    Bud
    -0.08
     હો
    -0.08
     હો�
    -0.08
    onomie
    -0.08
    POSITIVE LOGITS
     cash
    0.09
    yj
    0.08
     throws
    0.07
    /-
    0.07
     hearts
    0.07
     deeper
    0.07
     выход
    0.07
    现金
    0.07
     dilution
    0.07
     contacten
    0.07
    Act Density 0.005%

    No Known Activations