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

    Neuronpedia

    INDEX
    Explanations

    Java/Kotlin code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    endid
    -0.07
    _pan
    -0.07
    .ends
    -0.07
     designs
    -0.07
    מוזיאון
    -0.06
    Destination
    -0.06
     planet
    -0.06
    -interface
    -0.06
     ninguna
    -0.06
     NEGLIGENCE
    -0.06
    POSITIVE LOGITS
    ("",
    0.07
    (metrics
    0.07
    ****/↵
    0.07
    мо
    0.07
     metrics
    0.07
    时任
    0.07
    said
    0.07
    :");↵
    0.07
    }}>↵
    0.07
    复查
    0.07
    Act Density 0.084%

    No Known Activations