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

    Neuronpedia

    INDEX
    Explanations

    They

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     behavioral
    -0.07
     Зем
    -0.07
    럽
    -0.06
     rocky
    -0.06
     Boone
    -0.06
    BTC
    -0.06
     behavioural
    -0.06
     Rex
    -0.06
    -responsive
    -0.06
    "P
    -0.06
    POSITIVE LOGITS
    _write
    0.06
    违
    0.06
    itate
    0.06
    rawing
    0.06
    _Object
    0.06
     Flatten
    0.06
    _{
    0.06
    /{{
    0.06
     Spo
    0.06
    超过
    0.06
    Act Density 0.040%

    No Known Activations