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

    Neuronpedia

    INDEX
    Explanations

    plus or minus

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     maternity
    -0.09
     Fi
    -0.07
    ombie
    -0.07
     veh
    -0.06
    _COMPLEX
    -0.06
     باز
    -0.06
    Extract
    -0.06
     Comput
    -0.06
    _Struct
    -0.06
    .dateFormat
    -0.06
    POSITIVE LOGITS
     ±
    0.08
    +s
    0.07
     diverse
    0.07
     rewarding
    0.07
                ↵            ↵
    0.06
    ±
    0.06
    .findAll
    0.06
    )"},↵
    0.06
    Berry
    0.06
     team
    0.06
    Act Density 0.004%

    No Known Activations