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

    Neuronpedia

    INDEX
    Explanations

    cryptographic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    㞰
    0.45
    haviours
    0.41
    湋
    0.40
    ⾯
    0.39
     ستر
    0.39
     Alber
    0.38
    阿里
    0.38
     શહે
    0.38
    弜
    0.38
    toluene
    0.38
    POSITIVE LOGITS
     couldn
    0.46
    legte
    0.45
     can
    0.43
     prognostic
    0.43
     offense
    0.43
     block
    0.41
     progn
    0.41
     shots
    0.41
     team
    0.41
     lost
    0.41
    Act Density 0.000%

    No Known Activations