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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Vader
    -0.06
     khảo
    -0.06
     sailor
    -0.06
     Lear
    -0.06
    ционный
    -0.06
     UIImage
    -0.06
     Sailor
    -0.06
     bunun
    -0.06
    Он
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    ा।↵↵
    0.07
    _CAPTURE
    0.07
    upt
    0.06
    .est
    0.06
    _eval
    0.06
     ---------------------------------------------------------------------------↵
    0.06
    ArrayType
    0.06
    />
    0.06
    」↵
    0.06
     Sinh
    0.06
    Act Density 0.000%

    No Known Activations