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

    Neuronpedia

    INDEX
    Explanations

    very

    np_max-act · gemini-2.0-flash

    This neuron doesn’t detect or respond to any specific text patterns—it remains inactive.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    France
    -0.07
    칠
    -0.07
    aso
    -0.07
     leaking
    -0.07
    _Att
    -0.07
     Devil
    -0.06
     Рус
    -0.06
     talking
    -0.06
    'Brien
    -0.06
     Brown
    -0.06
    POSITIVE LOGITS
     very
    0.09
     Very
    0.08
    ’я
    0.08
     downright
    0.08
    (move
    0.07
     самых
    0.07
    (varargin
    0.07
    bed
    0.07
     červ
    0.06
    ARY
    0.06
    Act Density 0.007%

    No Known Activations