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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pantry
    -0.07
     jailed
    -0.07
     compét
    -0.07
    ιας
    -0.07
     حين
    -0.07
     skutečně
    -0.06
     narrator
    -0.06
    .weights
    -0.06
    _dicts
    -0.06
     niž
    -0.06
    POSITIVE LOGITS
    _identifier
    0.07
     Gothic
    0.07
    Wallet
    0.06
     Pitt
    0.06
    ZIP
    0.06
    getCell
    0.06
    _hero
    0.06
     Roberto
    0.06
     clearance
    0.06
     Counseling
    0.06
    Act Density 0.000%

    No Known Activations