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

    Neuronpedia

    INDEX
    Explanations

    say "B" words

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    erals
    0.88
    othing
    0.87
    era
    0.85
    ery
    0.84
    éro
    0.82
    erala
    0.82
    yam
    0.81
    arest
    0.81
    ürlich
    0.81
    edy
    0.81
    POSITIVE LOGITS
     Bead
    0.91
     bean
    0.89
     Hive
    0.88
     bead
    0.87
     beaver
    0.86
     Beacon
    0.86
     ప్
    0.86
     pl
    0.83
     Beaver
    0.82
     HV
    0.82
    Act Density 0.000%

    No Known Activations