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

    Neuronpedia

    INDEX
    Explanations

    add more

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cauliflower
    1.85
    )
    1.79
    ங்கிணை
    1.72
    ())));
    1.69
    <0x80>
    1.68
     underestimates
    1.67
    )))
    1.63
    );
    1.60
     abiert
    1.59
     étab
    1.55
    POSITIVE LOGITS
    itionally
    2.14
    dır
    2.03
    itrile
    2.03
    ла
    2.00
    itively
    1.91
    b
    1.91
    d
    1.88
    n
    1.86
    ون
    1.84
    itions
    1.74
    Act Density 0.354%

    No Known Activations