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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    onomy
    -0.07
    _MAP
    -0.07
    _AB
    -0.07
    _para
    -0.07
    а�
    -0.06
    Timeout
    -0.06
    Ι
    -0.06
    Modules
    -0.06
    "sync
    -0.06
    应该
    -0.06
    POSITIVE LOGITS
     adaptor
    0.07
     unnatural
    0.07
     інформа
    0.06
     روح
    0.06
     Bever
    0.06
    ylvania
    0.06
    olutions
    0.06
     savaş
    0.06
     플
    0.06
     Petr
    0.06
    Act Density 0.001%

    No Known Activations