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

    Neuronpedia

    INDEX
    Explanations

    contract

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    nas
    -0.07
     axiom
    -0.06
    "
    -0.06
    NAS
    -0.06
     converged
    -0.06
    러리
    -0.06
     стен
    -0.06
    button
    -0.06
     ":
    -0.06
     argparse
    -0.06
    POSITIVE LOGITS
    healthy
    0.07
    _guest
    0.06
    업체
    0.06
     Qatar
    0.06
     regenerate
    0.06
    tuğ
    0.06
    putc
    0.06
    لیل
    0.06
    _inp
    0.06
     outpatient
    0.06
    Act Density 0.012%

    No Known Activations