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

    Neuronpedia

    INDEX
    Explanations

    T

    np_max-act · gemini-2.0-flash

    The neuron is tuned to detect temperature‐related tokens (e.g. “T = … K” entries) in experimental data sections.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Bride
    -0.07
    148
    -0.06
    isp
    -0.06
     incarnation
    -0.06
     Girl
    -0.06
    436
    -0.06
    448
    -0.06
    (grammarAccess
    -0.06
     ergonomic
    -0.06
    158
    -0.06
    POSITIVE LOGITS
     Comparable
    0.07
    ُل
    0.07
    _TIMES
    0.06
    _TARGET
    0.06
     ευ
    0.06
     öff
    0.06
     NOI
    0.06
    !,↵
    0.06
     enth
    0.06
    лива
    0.06
    Act Density 0.000%

    No Known Activations