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

    Neuronpedia

    INDEX
    Explanations

    prompts

    np_max-act · gemini-2.0-flash

    The neuron detects occurrences of the word “prompt” (and its close variants) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    τογραφ
    -0.07
    irectory
    -0.07
     Publishing
    -0.07
    .cursor
    -0.06
    ิเวณ
    -0.06
    Ross
    -0.06
    Ant
    -0.06
    막
    -0.06
     진행
    -0.06
     slur
    -0.06
    POSITIVE LOGITS
    >'.
    0.06
    _IC
    0.06
    toa
    0.06
    tog
    0.06
    styled
    0.06
     gio
    0.06
     tad
    0.06
     Norfolk
    0.06
    .removeClass
    0.06
    @FindBy
    0.06
    Act Density 0.009%

    No Known Activations