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

    Neuronpedia

    INDEX
    Explanations

    chemical compounds

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ﳑ
    -0.07
     Trend
    -0.07
    �
    -0.07
    Defense
    -0.07
     Weird
    -0.06
    FULL
    -0.06
    \"]
    -0.06
    AYER
    -0.06
     celebr
    -0.06
    Compression
    -0.06
    POSITIVE LOGITS
     hài
    0.08
    .float
    0.07
     investigación
    0.07
    爸
    0.07
    dba
    0.06
     toilet
    0.06
    ܬ
    0.06
    _te
    0.06
     bas
    0.06
    贻
    0.06
    Act Density 0.006%

    No Known Activations