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

    Neuronpedia

    INDEX
    Explanations

    software development

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wcześ
    -0.09
    HC
    -0.08
     banget
    -0.08
     للغاية
    -0.08
    连
    -0.07
    elier
    -0.07
     osób
    -0.07
     autore
    -0.07
    acias
    -0.07
     auparavant
    -0.07
    POSITIVE LOGITS
     साव
    0.09
     painstaking
    0.09
     દરમ
    0.09
     ggf
    0.08
     specs
    0.08
     meticulously
    0.08
    poi
    0.08
     specifics
    0.08
     finalmente
    0.08
     drafts
    0.08
    Act Density 0.053%

    No Known Activations