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

    Neuronpedia

    INDEX
    Explanations

    als

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .wall
    -0.07
     Berkshire
    -0.07
    Super
    -0.07
    exual
    -0.07
    /res
    -0.06
    Battle
    -0.06
    дат
    -0.06
    .fhir
    -0.06
     degrade
    -0.06
    .repaint
    -0.06
    POSITIVE LOGITS
    Ha
    0.07
    openh
    0.07
     확
    0.07
     dean
    0.06
    DEV
    0.06
    ΩΣ
    0.06
    发现
    0.06
     اهل
    0.06
    론
    0.06
     secara
    0.06
    Act Density 0.427%

    No Known Activations