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

    Neuronpedia

    INDEX
    Explanations

    web development

    np_max-act · gemini-2.0-flash

    The neuron detects imperative, step‐by‐step instructional language (commands and task‐list steps).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     paved
    -0.07
    aman
    -0.06
    zet
    -0.06
    ير
    -0.06
    urai
    -0.06
    рук
    -0.06
     یعنی
    -0.06
     fit
    -0.06
    ाहन
    -0.06
     Fit
    -0.06
    POSITIVE LOGITS
    ipeg
    0.07
    expanded
    0.07
    Keeper
    0.06
     bunny
    0.06
     PTR
    0.06
    .')
    0.06
     Girlfriend
    0.06
     nerve
    0.06
    specs
    0.06
    }px
    0.06
    Act Density 0.091%

    No Known Activations