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

    Neuronpedia

    INDEX
    Explanations

    time

    np_max-act · gemini-2.0-flash

    The neuron primarily activates on mentions of “time series” (and related tokens in that time-based data context).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Johns
    -0.07
    _polygon
    -0.06
    _jump
    -0.06
     Phelps
    -0.06
    Protect
    -0.06
    .BorderSize
    -0.06
    rites
    -0.06
    ktop
    -0.06
    Roger
    -0.06
     brig
    -0.06
    POSITIVE LOGITS
     lựa
    0.07
     /****************************************************************
    0.07
     atas
    0.07
     comenz
    0.07
    .GeneratedValue
    0.07
     cargar
    0.06
    .gridx
    0.06
    분
    0.06
    _addr
    0.06
    بالإنجليزية
    0.06
    Act Density 0.010%

    No Known Activations