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

    Neuronpedia

    INDEX
    Explanations

    oss

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    adam
    -0.07
    AVE
    -0.06
    INVAL
    -0.06
     aura
    -0.06
    ת
    -0.06
     planning
    -0.06
    _fake
    -0.06
    essed
    -0.06
    toi
    -0.06
    มา
    -0.06
    POSITIVE LOGITS
    AttributeValue
    0.07
     `\
    0.07
     ideology
    0.07
     lique
    0.07
     stojí
    0.06
    strlen
    0.06
     Petr
    0.06
     Watt
    0.06
    File
    0.06
     dbname
    0.06
    Act Density 0.001%

    No Known Activations