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

    Neuronpedia

    INDEX
    Explanations

    specific

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ј
    -0.07
    ERRQ
    -0.06
    VALUES
    -0.06
    _HOST
    -0.06
     Singular
    -0.06
     ellipse
    -0.06
    ('*',
    -0.06
    byn
    -0.06
     passengers
    -0.06
     Tumblr
    -0.06
    POSITIVE LOGITS
    manufacturer
    0.08
     Benedict
    0.07
     участие
    0.07
     chod
    0.06
    egr
    0.06
    Hum
    0.06
    Map
    0.06
    property
    0.06
     Hum
    0.06
    /basic
    0.06
    Act Density 0.012%

    No Known Activations