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

    Neuronpedia

    INDEX
    Explanations

    base

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of numeric base specifications (e.g. “base-8”, “base-2”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .calc
    -0.08
    rics
    -0.07
    ovolta
    -0.07
    терн
    -0.07
    اشت
    -0.07
    arrass
    -0.06
    796
    -0.06
    863
    -0.06
     PROC
    -0.06
     kel
    -0.06
    POSITIVE LOGITS
    iny
    0.07
     navr
    0.07
     druh
    0.06
     Dao
    0.06
    0.06
     sensed
    0.06
    implode
    0.06
     itertools
    0.06
     expresses
    0.06
     Farmer
    0.06
    Act Density 0.006%

    No Known Activations