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

    Neuronpedia

    INDEX
    Explanations

    file paths

    np_max-act · gemini-2.0-flash

    This neuron fires on tokens that are parts of filesystem paths (e.g. directory names like “Cellar” or “opt” in “/usr/local/Cellar” or “/opt/…”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Histogram
    -0.07
    gap
    -0.07
     beach
    -0.07
     insulated
    -0.07
     vulnerability
    -0.07
     hosting
    -0.07
     calculator
    -0.07
    NavController
    -0.06
     FCC
    -0.06
     Juliet
    -0.06
    POSITIVE LOGITS
    _tele
    0.06
    TEL
    0.06
     тех
    0.06
    _written
    0.06
    
    0.06
     sais
    0.06
     шаг
    0.06
     LastName
    0.06
    итися
    0.05
     �
    0.05
    Act Density 0.004%

    No Known Activations