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

    Neuronpedia

    INDEX
    Explanations

    funny

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (units
    -0.07
    .localPosition
    -0.07
    Steel
    -0.06
    _props
    -0.06
    ราค
    -0.06
     cancellationToken
    -0.06
     dveře
    -0.06
    steel
    -0.06
     reconstruction
    -0.06
    584
    -0.06
    POSITIVE LOGITS
     funny
    0.14
     hilarious
    0.09
     Funny
    0.08
    Funny
    0.08
     hilar
    0.07
     interesting
    0.07
     authenticated
    0.07
    .PL
    0.07
    妙
    0.06
     buried
    0.06
    Act Density 0.013%

    No Known Activations