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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cen
    -0.07
     جه
    -0.07
    .adv
    -0.06
     ys
    -0.06
     incarn
    -0.06
     Fischer
    -0.06
     kidn
    -0.06
     fv
    -0.06
    eten
    -0.06
    ิยม
    -0.06
    POSITIVE LOGITS
    _destroy
    0.07
     Wordpress
    0.06
    _WP
    0.06
     explicitly
    0.06
    <Response
    0.06
    runtime
    0.06
     dirección
    0.06
    quiring
    0.06
     instant
    0.06
     εισ
    0.06
    Act Density 0.052%

    No Known Activations