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

    Neuronpedia

    INDEX
    Explanations

    form

    np_max-act · gemini-2.0-flash

    The neuron activates on advice emphasizing correct form or technique (e.g., “focus on proper form”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     abol
    -0.06
     abolished
    -0.06
    IRST
    -0.06
    获得
    -0.06
    isations
    -0.06
    Apache
    -0.06
    [last
    -0.06
    "L
    -0.06
    doesn
    -0.06
    =size
    -0.06
    POSITIVE LOGITS
     compromising
    0.08
     υπάρχ
    0.07
    trand
    0.07
    控制
    0.07
    csrf
    0.07
     }}}
    0.07
    なんて
    0.07
     gourmet
    0.06
    ينا
    0.06
     лучше
    0.06
    Act Density 0.018%

    No Known Activations