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

    Neuronpedia

    INDEX
    Explanations

    Long and complex passages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    MAP
    -0.07
    abort
    -0.07
    (names
    -0.07
     magnetic
    -0.07
    PRETTY
    -0.06
    .voice
    -0.06
    _man
    -0.06
    uos
    -0.06
    rippling
    -0.06
     degli
    -0.06
    POSITIVE LOGITS
    ibili
    0.07
     مارس
    0.06
     |
    0.06
    /videos
    0.06
     خارجية
    0.06
    輪
    0.06
     educator
    0.06
     Views
    0.06
    ÖL
    0.06
    _cancel
    0.06
    Act Density 0.000%

    No Known Activations