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

    Neuronpedia

    INDEX
    Explanations

    code punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     insp
    -0.08
    enli
    -0.07
    ’h
    -0.07
    elan
    -0.07
    itas
    -0.07
     GN
    -0.07
    eterangan
    -0.07
    ensis
    -0.07
     rah
    -0.07
     toestand
    -0.07
    POSITIVE LOGITS
     novamente
    0.09
    Again
    0.08
    again
    0.08
     വീണ്ടും
    0.08
     again
    0.08
     Again
    0.08
     nuevamente
    0.08
     שוב
    0.08
     IERC
    0.08
    േധ
    0.07
    Act Density 0.140%

    No Known Activations