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
    Iterations
    -0.07
     serialize
    -0.07
     normals
    -0.07
     Spatial
    -0.06
    .Cookie
    -0.06
     ore
    -0.06
    ossip
    -0.06
     Cait
    -0.06
    enta
    -0.06
     prohibits
    -0.06
    POSITIVE LOGITS
    tı
    0.07
     논
    0.07
     прямо
    0.06
    shortcode
    0.06
     είχαν
    0.06
     questa
    0.06
    formik
    0.06
    communic
    0.06
    SX
    0.06
     unarmed
    0.06
    Act Density 0.023%

    No Known Activations