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

    Neuronpedia

    INDEX
    Explanations

    affirmation and recommendation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     catechol
    0.57
    чну
    0.56
     graisse
    0.56
    :
    0.55
     urine
    0.53
     catech
    0.53
    areth
    0.52
     roadmap
    0.52
    urine
    0.52
    auw
    0.52
    POSITIVE LOGITS
    is
    0.65
    es
    0.58
    the
    0.57
    ות
    0.57
     Unternehmen
    0.55
    น
    0.55
     Į
    0.54
    in
    0.54
    ق
    0.53
    ת
    0.52
    Act Density 0.003%

    No Known Activations