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

    Neuronpedia

    INDEX
    Explanations

    text analysis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     doorstep
    -0.06
    Guid
    -0.06
    هـ
    -0.06
     cougar
    -0.06
    ̃
    -0.06
    ุมภาพ
    -0.06
    incr
    -0.05
    <a
    -0.05
    看见
    -0.05
    _inverse
    -0.05
    POSITIVE LOGITS
     restarted
    0.08
    alem
    0.08
     historian
    0.07
    珍
    0.07
    riteln
    0.07
    فه
    0.07
    Ctrls
    0.07
    ево
    0.06
     Guard
    0.06
    яет
    0.06
    Act Density 0.050%

    No Known Activations