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

    Neuronpedia

    INDEX
    Explanations

    same

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    doFilter
    0.60
    üb
    0.57
     ontv
    0.55
    defender
    0.55
    bouncer
    0.54
    vect
    0.54
    validator
    0.54
    数为
    0.53
     wäre
    0.53
     Juda
    0.52
    POSITIVE LOGITS
    rani
    0.63
     забезпечення
    0.61
     instantaneous
    0.61
     cuisson
    0.60
     elimination
    0.59
    幸福
    0.58
     приготовления
    0.57
    刚好
    0.57
    ristmas
    0.57
     fissures
    0.57
    Act Density 0.000%

    No Known Activations