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

    Neuronpedia

    INDEX
    Explanations

    neuro

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cand
    -0.07
    周期
    -0.07
     touching
    -0.07
     Guid
    -0.06
    SPEC
    -0.06
     FX
    -0.06
     sandy
    -0.06
    拥
    -0.06
     Long
    -0.06
     режим
    -0.06
    POSITIVE LOGITS
     namespaces
    0.07
    _OLD
    0.06
     ambos
    0.06
    Symbols
    0.06
    _processor
    0.06
     homosexuals
    0.06
     ça
    0.06
     handwritten
    0.06
    Ін
    0.06
    omet
    0.06
    Act Density 0.007%

    No Known Activations