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

    Neuronpedia

    INDEX
    Explanations

    computer code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     recipes
    -0.06
     CAS
    -0.06
     severity
    -0.06
     Severity
    -0.06
     limitations
    -0.06
    compet
    -0.06
     Detector
    -0.06
    aur
    -0.05
     Fault
    -0.05
     MOST
    -0.05
    POSITIVE LOGITS
    estinal
    0.07
    しま
    0.07
     गई
    0.06
    ージ
    0.06
     ACLU
    0.06
     homelessness
    0.06
    _wind
    0.06
    .fasta
    0.06
    [child
    0.06
    STRU
    0.06
    Act Density 0.012%

    No Known Activations