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

    Neuronpedia

    INDEX
    Explanations

    Suffixes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     жар
    -0.07
    draw
    -0.07
     Charset
    -0.07
     tor
    -0.07
    _SOFT
    -0.07
    /block
    -0.06
    _picture
    -0.06
    stdio
    -0.06
     tx
    -0.06
    _BUS
    -0.06
    POSITIVE LOGITS
     vulnerability
    0.08
     referred
    0.06
     mediated
    0.06
    Dump
    0.06
     цін
    0.06
     SUR
    0.06
     Profiles
    0.06
     Hyp
    0.06
    她们
    0.06
     पढ
    0.06
    Act Density 0.003%

    No Known Activations