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

    Neuronpedia

    INDEX
    Explanations

    experiments with cells

    np_max-act · gemini-2.0-flash

    This neuron detects methodological action verbs describing experimental procedures (e.g., treated, stimulated, incubated).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    038
    -0.07
    744
    -0.07
     �
    -0.07
    _validator
    -0.06
    ı
    -0.06
    842
    -0.06
     ف
    -0.06
     şüph
    -0.06
    441
    -0.06
    044
    -0.06
    POSITIVE LOGITS
     prompts
    0.08
     yılında
    0.07
     عليه
    0.06
    September
    0.06
     attribution
    0.06
    boxes
    0.06
    нув
    0.06
     reminded
    0.06
    -century
    0.06
    Foreground
    0.06
    Act Density 0.027%

    No Known Activations