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

    Neuronpedia

    INDEX
    Explanations

    oc

    np_max-act · gemini-2.0-flash

    This neuron flags sequences of Cyrillic characters (i.e. Russian text segments) embedded in the input.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    arga
    -0.08
    FORM
    -0.07
     JpaRepository
    -0.07
    _matrix
    -0.07
     religious
    -0.06
     Yelp
    -0.06
    _MISSING
    -0.06
    ripple
    -0.06
    láš
    -0.06
    _view
    -0.06
    POSITIVE LOGITS
     agr
    0.07
    chef
    0.06
     Haley
    0.06
    Rev
    0.06
     перев
    0.06
    �
    0.06
    Vel
    0.06
    ey
    0.06
    Hola
    0.06
    发生
    0.06
    Act Density 0.012%

    No Known Activations