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

    Neuronpedia

    INDEX
    Explanations

    math equations

    np_max-act · gemini-2.0-flash

    This neuron is effectively “dead,” as it does not activate on any tokens (it never finds a matching pattern).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Gtk
    -0.07
     riding
    -0.06
    //*
    -0.06
     ست
    -0.06
     تت
    -0.06
     python
    -0.06
    722
    -0.06
    GOR
    -0.06
    (""))↵
    -0.06
     Adams
    -0.06
    POSITIVE LOGITS
     domain
    0.07
     yine
    0.07
    '],
↵
    0.06
    ę
    0.06
    وار
    0.06
    bildung
    0.06
    MethodName
    0.06
    ximity
    0.06
     mold
    0.06
     sản
    0.06
    Act Density 0.001%

    No Known Activations