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

    Neuronpedia

    INDEX
    Explanations

    Hebrew

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect Hebrew characters or tokens in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     emoc
    -0.07
     peč
    -0.07
    ':''
    -0.06
    .`|`↵
    -0.06
     Piano
    -0.06
    ené
    -0.06
     江
    -0.06
     дит
    -0.06
    _TIMEOUT
    -0.06
    odia
    -0.06
    POSITIVE LOGITS
     Book
    0.07
     deriving
    0.06
    _ne
    0.06
     componente
    0.06
    .userData
    0.06
     because
    0.06
    вали
    0.06
    声音
    0.06
    -Americans
    0.06
    siblings
    0.06
    Act Density 0.025%

    No Known Activations