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

    Neuronpedia

    INDEX
    Explanations

    sentence separators

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /bower
    -0.07
    Since
    -0.07
     Lighting
    -0.07
    =model
    -0.06
    eld
    -0.06
     Feld
    -0.06
    _max
    -0.06
    _limits
    -0.06
    Ja
    -0.06
    _meta
    -0.06
    POSITIVE LOGITS
    ?>/
    0.07
    ΑΝΤ
    0.06
    (ConfigurationManager
    0.06
     Guantanamo
    0.06
    enzie
    0.06
     YM
    0.06
    едаг
    0.06
     Γκ
    0.06
     grandma
    0.05
    ozy
    0.05
    Act Density 0.126%

    No Known Activations