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

    Neuronpedia

    INDEX
    Explanations

    say "="

    np_max-act-logits · gemini-2.0-flash

    mathematical expressions with addition operations.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @jacktpayne51
    New Auto-Interp
    Negative Logits
     geweest
    -0.12
     избежать
    -0.09
    ák
    -0.09
     були
    -0.09
     métier
    -0.09
     Año
    -0.09
     *↵//
    -0.08
     acredito
    -0.08
     применять
    -0.08
    ежать
    -0.08
    POSITIVE LOGITS
     asks
    0.08
     property
    0.08
     dams
    0.07
    @property
    0.07
    74
    0.07
     submissions
    0.07
     suggests
    0.07
     seven
    0.07
    (property
    0.07
     പറയുന്നു
    0.07
    Act Density 0.020%

    No Known Activations