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

    Neuronpedia

    INDEX
    Explanations

    code identifiers

    np_max-act · gemini-2.0-flash

    The neuron fires on backslash-escaped hexadecimal code sequences in string literals (e.g. “\f0e…” in CSS content properties).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    motor
    -0.06
    	startActivity
    -0.06
    analy
    -0.06
     تی
    -0.06
     vag
    -0.06
    झ
    -0.06
    asString
    -0.06
    ště
    -0.06
    likelihood
    -0.06
    ییر
    -0.06
    POSITIVE LOGITS
    ابق
    0.07
     zřejmě
    0.07
    _Name
    0.07
     Dream
    0.06
     //↵
    0.06
    (sym
    0.06
     happier
    0.06
    �
    0.06
    níci
    0.06
     freeway
    0.06
    Act Density 0.001%

    No Known Activations