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

    Neuronpedia

    INDEX
    Explanations

    chrome and rs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    or
    1.30
    unately
    1.20
    ે
    1.16
    an
    1.13
    s
    1.07
    żenia
    1.05
    lo
    1.04
    𝓬
    1.04
    er
    1.02
    ת
    1.01
    POSITIVE LOGITS
     Privat
    1.08
     eben
    1.08
     ess
    1.07
     menet
    1.04
    HeaderText
    1.00
     όσο
    1.00
     enne
    0.97
    وس
    0.97
     terwijl
    0.97
    まずは
    0.95
    Act Density 0.005%

    No Known Activations