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

    Neuronpedia

    INDEX
    Explanations

    Latex math syntax, formulas, and expressions.

    oai_token-act-pair · gemini-2.0-flash

    Arrows

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    +#+
    -0.71
     nakalista
    -0.66
     ujednoznacz
    -0.65
    تقاوى
    -0.64
    ImageContext
    -0.63
    matchCondition
    -0.63
     cdti
    -0.61
     cheek
    -0.59
    //
    -0.58
     Cheek
    -0.55
    POSITIVE LOGITS
     →
    0.98
     ->
    0.95
    ->
    0.91
    →
    0.88
    ]->
    0.76
     -->
    0.69
    )->
    0.68
     =>
    0.68
    -->
    0.64
    rightarrow
    0.62
    Act Density 2.544%

    No Known Activations