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

    Neuronpedia

    INDEX
    Explanations

    assessments or checks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    集
    -0.06
    xx
    -0.06
     vice
    -0.06
    Paren
    -0.06
     集
    -0.06
    .mean
    -0.06
    .tar
    -0.06
    .getAttribute
    -0.06
    ietet
    -0.06
    eft
    -0.06
    POSITIVE LOGITS
     culp
    0.07
    PLIED
    0.07
     kms
    0.07
    (SC
    0.07
    "display
    0.07
     دریا
    0.06
    tul
    0.06
     ऋ
    0.06
     surpass
    0.06
    submitButton
    0.06
    Act Density 0.064%

    No Known Activations