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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     соверш
    -0.08
    ().↵
    -0.07
     registering
    -0.07
     infuri
    -0.07
    艟
    -0.07
     instincts
    -0.07
     gangbang
    -0.06
     strike
    -0.06
     dünyanın
    -0.06
    )?↵
    -0.06
    POSITIVE LOGITS
    _ip
    0.07
     DIN
    0.07
    杜兰
    0.06
    튼
    0.06
     lad
    0.06
     liquor
    0.06
    /W
    0.06
    .env
    0.06
     rape
    0.06
    (<
    0.06
    Act Density 0.061%

    No Known Activations