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

    Neuronpedia

    INDEX
    Explanations

    364

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric literals (integer tokens) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    JNIEnv
    -0.07
    (pDX
    -0.06
    jad
    -0.06
     �
    -0.06
    .saved
    -0.06
     بیم
    -0.06
    Pers
    -0.06
     flatten
    -0.06
    _Equals
    -0.06
    rag
    -0.06
    POSITIVE LOGITS
    醒
    0.07
     xr
    0.07
    eya
    0.07
    уска
    0.07
    -il
    0.06
    tera
    0.06
     أكتوبر
    0.06
     highway
    0.06
    _allow
    0.06
     Cadillac
    0.06
    Act Density 0.003%

    No Known Activations