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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oit
    -0.07
     expelled
    -0.07
    otros
    -0.07
     collector
    -0.07
     Pump
    -0.06
     rolled
    -0.06
    _Password
    -0.06
    .foreach
    -0.06
    VALUES
    -0.06
    ROID
    -0.06
    POSITIVE LOGITS
    __).
    0.07
    _update
    0.06
    ..↵
    0.06
    ↵
    0.06
    )↵↵
    0.06
    ↵↵
    0.06
     imagin
    0.06
    polate
    0.06
    .')↵↵
    0.06
    สถาน
    0.06
    Act Density 0.000%

    No Known Activations