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

    Neuronpedia

    INDEX
    Explanations

    dose

    np_max-act · gemini-2.0-flash

    The neuron detects numeric quantitative measurement contexts, especially dose- and time-dependent values.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    stars
    -0.07
    020
    -0.07
    oxy
    -0.07
    unction
    -0.06
     stumbled
    -0.06
     Oaks
    -0.06
    ************
    -0.06
    ActivityIndicator
    -0.06
    assigned
    -0.06
    icy
    -0.06
    POSITIVE LOGITS
     Oslo
    0.06
     spol
    0.06
     香港
    0.06
     घटन
    0.06
     strm
    0.06
    
    0.06
     layers
    0.06
     کنند
    0.06
     closer
    0.06
    stup
    0.06
    Act Density 0.008%

    No Known Activations