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

    Neuronpedia

    INDEX
    Explanations

    task

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ことに
    -0.06
    Paren
    -0.06
     Demon
    -0.06
    Tour
    -0.06
    Combo
    -0.06
     Filter
    -0.06
    .resize
    -0.06
     nuit
    -0.06
     Shows
    -0.06
     Esta
    -0.06
    POSITIVE LOGITS
     tốt
    0.07
    encial
    0.06
    ращ
    0.06
    quirrel
    0.06
    -focused
    0.06
    aturity
    0.06
    اقل
    0.06
    wind
    0.06
    (Core
    0.06
    imate
    0.06
    Act Density 0.000%

    No Known Activations