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

    Neuronpedia

    INDEX
    Explanations

    True

    np_max-act · gemini-2.0-flash

    The neuron fires whenever the text is giving a Boolean answer (the tokens “True” or “False”) to one of these numeric‐comparison questions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    (mappedBy
    -0.07
    маз
    -0.07
     burada
    -0.07
    �
    -0.06
    .toByteArray
    -0.06
    /Error
    -0.06
    (...)
    -0.06
    �
    -0.06
     endiş
    -0.06
    (...
    -0.06
    POSITIVE LOGITS
    으면
    0.07
    .currentTarget
    0.07
    らせ
    0.07
    beh
    0.07
     visuals
    0.06
     foundation
    0.06
     """
↵
↵
    0.06
    _commit
    0.06
     routed
    0.06
     commentaire
    0.06
    Act Density 0.002%

    No Known Activations