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

    Neuronpedia

    INDEX
    Explanations

    html

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    311
    -0.08
     Faul
    -0.06
    pile
    -0.06
    šlo
    -0.06
     Gad
    -0.06
    612
    -0.06
    815
    -0.06
     Race
    -0.06
     nonce
    -0.06
     Τε
    -0.06
    POSITIVE LOGITS
     touches
    0.07
    _Destroy
    0.07
     staat
    0.06
    gorith
    0.06
    {};↵
    0.06
    lparr
    0.06
    ffects
    0.06
    ricanes
    0.06
     gỗ
    0.06
     İs
    0.06
    Act Density 0.002%

    No Known Activations