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

    Neuronpedia

    INDEX
    Explanations

    code/software

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .check
    -0.07
     يم
    -0.07
    хи
    -0.07
     Checks
    -0.07
    Executing
    -0.07
    selector
    -0.06
     tables
    -0.06
     لب
    -0.06
     Panels
    -0.06
    bad
    -0.06
    POSITIVE LOGITS
    87
    0.07
    93
    0.06
    _RECE
    0.06
    BIG
    0.06
     merciless
    0.06
    99
    0.06
     onHide
    0.06
    48
    0.06
    Philadelphia
    0.06
     CLLocation
    0.06
    Act Density 0.000%

    No Known Activations