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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rani
    -0.07
    كور
    -0.06
     province
    -0.06
    owych
    -0.06
     över
    -0.06
     puntos
    -0.06
     willen
    -0.06
     Lodge
    -0.06
    apture
    -0.06
    _CNT
    -0.06
    POSITIVE LOGITS
    再
    0.07
     відповідаль
    0.07
     маст
    0.06
     celestial
    0.06
    stars
    0.06
    �
    0.06
    CONNECT
    0.06
     tricks
    0.06
    snippet
    0.06
    лач
    0.06
    Act Density 0.004%

    No Known Activations