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
    .Users
    -0.07
    .cent
    -0.06
    逸
    -0.06
     عبد
    -0.06
    Slf
    -0.06
     �
    -0.06
    ool
    -0.06
    ALTH
    -0.06
    -Speed
    -0.06
     EVER
    -0.06
    POSITIVE LOGITS
    уляр
    0.06
     Frozen
    0.06
     materia
    0.06
    prisingly
    0.06
    -scroll
    0.06
    ılıç
    0.06
     ενός
    0.06
    _roi
    0.06
     EU
    0.06
    ivariate
    0.06
    Act Density 0.008%

    No Known Activations