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

    Neuronpedia

    INDEX
    Explanations

    markdown list punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cartoons
    -0.07
     garlic
    -0.07
    stead
    -0.06
    separator
    -0.06
     daemon
    -0.06
     Usage
    -0.06
    (Control
    -0.06
     dv
    -0.06
    lambda
    -0.06
     ford
    -0.06
    POSITIVE LOGITS
     oček
    0.07
     cherish
    0.06
    智能
    0.06
     düzenlem
    0.06
    少し
    0.06
    iology
    0.06
    _COORD
    0.06
    reesome
    0.06
    inea
    0.06
    ้ม
    0.06
    Act Density 0.068%

    No Known Activations