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

    Neuronpedia

    INDEX
    Explanations

    and,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     earners
    -0.07
     spared
    -0.07
    erson
    -0.07
     nearby
    -0.06
     amigo
    -0.06
     binder
    -0.06
    ันได
    -0.06
    DRAM
    -0.06
     grands
    -0.06
     \<
    -0.06
    POSITIVE LOGITS
    .TXT
    0.07
    SDL
    0.06
    _uuid
    0.06
    RD
    0.06
    .getMonth
    0.06
    �
    0.06
    zzle
    0.06
     иг
    0.06
    олн
    0.06
    ("("
    0.06
    Act Density 0.009%

    No Known Activations