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

    Neuronpedia

    INDEX
    Explanations

    me

    np_max-act · gemini-2.0-flash

    The neuron specifically detects and activates on tokens that are floating‐point numbers (i.e. decimal numerals).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ru
    -0.07
     від
    -0.06
    stoi
    -0.06
    ーロ
    -0.06
    ond
    -0.06
     Gameplay
    -0.06
     intim
    -0.06
     Franklin
    -0.06
     Him
    -0.05
     Photon
    -0.05
    POSITIVE LOGITS
    signature
    0.07
     numeric
    0.07
    meer
    0.07
     определ
    0.06
    numer
    0.06
    ;base
    0.06
     kèm
    0.06
    seo
    0.06
     Орг
    0.06
    Adresse
    0.06
    Act Density 0.026%

    No Known Activations