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

    Neuronpedia

    INDEX
    Explanations

    in detail

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    \|,
    0.88
     addition
    0.88
     якості
    0.84
    middels
    0.80
     některé
    0.80
     tillegg
    0.75
     niektórych
    0.75
     países
    0.74
    addition
    0.74
     někter
    0.73
    POSITIVE LOGITS
     entier
    0.77
     implications
    0.77
     intentions
    0.72
    detail
    0.71
     manne
    0.70
     details
    0.70
     तरीके
    0.69
     detail
    0.67
     Details
    0.66
    details
    0.66
    Act Density 0.080%

    No Known Activations