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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     uděl
    -0.08
    okedex
    -0.07
     regenerated
    -0.07
    RIORITY
    -0.07
    _added
    -0.07
    aterangepicker
    -0.07
     хозяй
    -0.07
    ائع
    -0.07
    urchase
    -0.06
    سية
    -0.06
    POSITIVE LOGITS
    disk
    0.07
    tested
    0.07
     Motorola
    0.07
    音乐
    0.06
    TRUE
    0.06
    adf
    0.06
     Chester
    0.06
     phantom
    0.06
    dismiss
    0.06
    -val
    0.06
    Act Density 0.018%

    No Known Activations