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

    Neuronpedia

    INDEX
    Explanations

    5

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens—i.e. digits and measured values (numbers, decimals) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     psychology
    -0.08
     بخ
    -0.07
    ू
    -0.07
     analytic
    -0.06
    DDS
    -0.06
    \Request
    -0.06
    Mission
    -0.06
     Dx
    -0.06
    誤
    -0.06
     ASSIGN
    -0.06
    POSITIVE LOGITS
    $res
    0.06
    Rib
    0.06
    .Multi
    0.06
    fik
    0.06
    ])**
    0.06
    χία
    0.05
    _folders
    0.05
    Pres
    0.05
    _TRAN
    0.05
     Painter
    0.05
    Act Density 0.015%

    No Known Activations