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

    Neuronpedia

    INDEX
    Explanations

    always

    np_max-act · gemini-2.0-flash

    This neuron activates on floating‐point numeric literals (decimal numbers with fractional parts).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Zhu
    -0.07
    774
    -0.07
     Без
    -0.06
    Τα
    -0.06
     Fam
    -0.06
    Img
    -0.06
     Eisen
    -0.06
     wastes
    -0.06
    MV
    -0.06
    .dequeueReusableCell
    -0.06
    POSITIVE LOGITS
    osloven
    0.07
    şt
    0.07
    USD
    0.07
     Bild
    0.06
     komen
    0.06
     Organizer
    0.06
     beacon
    0.06
    ọn
    0.06
    ัน
    0.06
     serpent
    0.06
    Act Density 0.032%

    No Known Activations