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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .hp
    -0.07
     اختل
    -0.07
     shaders
    -0.07
    시험
    -0.06
    .SEVERE
    -0.06
    (forms
    -0.06
    slideUp
    -0.06
    ;base
    -0.06
    _skill
    -0.06
     채용
    -0.06
    POSITIVE LOGITS
     echo
    0.08
     wrapped
    0.07
    Anchor
    0.06
     Breaking
    0.06
    aintenance
    0.06
     거
    0.06
     meshes
    0.06
     ridiculously
    0.06
    echo
    0.06
    _lock
    0.06
    Act Density 0.018%

    No Known Activations