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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    χ
    -0.08
    电视机
    -0.07
    Demo
    -0.07
    辞
    -0.07
    紀
    -0.07
     legacy
    -0.07
    𬟽
    -0.07
    _err
    -0.07
     소
    -0.06
    emode
    -0.06
    POSITIVE LOGITS
    ünkü
    0.08
    压实
    0.07
     אמר
    0.07
     Proper
    0.07
     Plan
    0.07
     układ
    0.07
     yapıl
    0.07
     Planner
    0.07
     Superintendent
    0.07
    (parseInt
    0.07
    Act Density 0.067%

    No Known Activations