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

    Neuronpedia

    INDEX
    Explanations

    database access

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .getDefault
    -0.07
     대학
    -0.06
     کننده
    -0.06
     '').
    -0.06
     dew
    -0.06
     lục
    -0.06
     NodeType
    -0.06
    хо
    -0.06
     Με
    -0.06
    后
    -0.06
    POSITIVE LOGITS
    \.
    0.07
     troubling
    0.07
     moci
    0.07
     handsome
    0.06
    strap
    0.06
     hesab
    0.06
     Discord
    0.06
     thankfully
    0.06
    _increment
    0.06
     hues
    0.06
    Act Density 0.021%

    No Known Activations