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

    Neuronpedia

    INDEX
    Explanations

    ingredient types and quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fish
    0.78
     poissons
    0.75
     residues
    0.74
     vestiges
    0.74
    fish
    0.72
     residuals
    0.71
     pescado
    0.71
    residual
    0.71
     tapas
    0.71
     prawns
    0.70
    POSITIVE LOGITS
     Ass
    0.70
     Medium
    0.66
    GINIA
    0.65
     Original
    0.65
     Welch
    0.65
     jumbo
    0.62
     assorted
    0.62
     Regular
    0.61
    Ass
    0.61
     medium
    0.61
    Act Density 0.151%

    No Known Activations