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

    Neuronpedia

    INDEX
    Explanations

    Code, dates, reports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     magasiner
    -0.55
    cipar
    -0.52
    amment
    -0.52
     Haft
    -0.51
     Mantel
    -0.51
     digress
    -0.50
    ilitatea
    -0.49
    AndGet
    -0.48
     normalement
    -0.47
    nagar
    -0.46
    POSITIVE LOGITS
    boo
    0.81
     boo
    0.79
     boos
    0.74
    sizeCache
    0.74
    Boo
    0.68
    BOO
    0.68
     BOO
    0.65
     Boo
    0.64
    ($__
    0.61
    boa
    0.60
    Act Density 0.001%

    No Known Activations