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

    Neuronpedia

    INDEX
    Explanations

    formula

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    蜜
    -0.07
    KP
    -0.07
     Merge
    -0.06
     getConnection
    -0.06
     assertEquals
    -0.06
    İY
    -0.06
    人才
    -0.06
    invest
    -0.06
    ंर
    -0.06
    .AL
    -0.06
    POSITIVE LOGITS
    (lambda
    0.07
     Sword
    0.07
     '{"
    0.06
    �
    0.06
     ""
↵
    0.06
    _hat
    0.06
    áct
    0.06
    Personally
    0.06
     Donna
    0.06
     AMAZ
    0.06
    Act Density 0.003%

    No Known Activations