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

    Neuronpedia

    INDEX
    Explanations

    "sto" or "stow" prefix

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.70
    aarrggbb
    -0.69
    Parcelize
    -0.63
    outSlope
    -0.63
    /*
    -0.60
     chi̍t
    -0.57
     Biôgrafia
    -0.55
    مصادر
    -0.55
    IsMutable
    -0.54
     AspNetCore
    -0.54
    POSITIVE LOGITS
     continúas
    0.56
    oped
    0.53
    PACE
    0.50
    pover
    0.50
    mach
    0.50
    thet
    0.49
    macht
    0.49
    testcase
    0.49
     matière
    0.47
     occupé
    0.47
    Act Density 0.003%

    No Known Activations