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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash

    This neuron activates on German words or phrases (marking passages written in German).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Wheels
    -0.07
    zv
    -0.07
     vict
    -0.06
    annotations
    -0.06
     td
    -0.06
     держав
    -0.06
    UpdatedAt
    -0.06
    (vis
    -0.06
     św
    -0.06
    "As
    -0.06
    POSITIVE LOGITS
    	operator
    0.07
     στους
    0.07
    (random
    0.07
     amazon
    0.06
    .place
    0.06
    SQLException
    0.06
    _parser
    0.06
    reduce
    0.06
    ction
    0.06
     jogador
    0.06
    Act Density 0.039%

    No Known Activations