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

    Neuronpedia

    INDEX
    Explanations

    names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .spin
    -0.07
     []↵↵
    -0.06
    Rich
    -0.06
     '#
    -0.06
    SS
    -0.06
    ในป
    -0.06
     pickle
    -0.06
    )));↵↵
    -0.06
    Alamat
    -0.06
    трон
    -0.06
    POSITIVE LOGITS
     encoded
    0.07
     вида
    0.06
    _BREAK
    0.06
    ano
    0.06
     Chuck
    0.06
     ADM
    0.06
     jednou
    0.06
     bud
    0.06
     excluding
    0.06
     (“
    0.06
    Act Density 0.075%

    No Known Activations