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

    Neuronpedia

    INDEX
    Explanations

    presentation, question, Poker, shadows

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     chipping
    0.39
    chk
    0.38
    atively
    0.37
    čin
    0.37
     tác
    0.36
    iglich
    0.36
    achar
    0.36
     bogey
    0.36
    hiba
    0.36
    кай
    0.36
    POSITIVE LOGITS
     personalizada
    0.42
     Washington
    0.41
    washington
    0.41
     Liquor
    0.37
     Conversation
    0.36
    फाली
    0.36
    Washington
    0.36
     которую
    0.36
    ष्ठ
    0.36
     ]:
    0.35
    Act Density 0.001%

    No Known Activations