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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    The neuron never fires—it doesn’t reliably detect any pattern in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     hlavu
    -0.07
    �
    -0.06
    razil
    -0.06
     sl
    -0.06
     Muham
    -0.06
     fv
    -0.06
     measurable
    -0.06
    ADATA
    -0.06
    dependent
    -0.06
    	ms
    -0.06
    POSITIVE LOGITS
    ές
    0.07
    _escape
    0.07
    _util
    0.06
    ={},
    0.06
     واقعی
    0.06
     قتل
    0.06
     proceeding
    0.06
    女
    0.06
    ньо
    0.06
     ülke
    0.06
    Act Density 0.023%

    No Known Activations