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

    Neuronpedia

    INDEX
    Explanations

    than

    np_max-act · gemini-2.0-flash

    This neuron activates on comparative or superlative words (e.g. “more,” “than,” “daring”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     competitor
    -0.06
     pied
    -0.06
    emia
    -0.06
     jaz
    -0.06
    .IsNotNull
    -0.06
    ové
    -0.06
    _ITER
    -0.06
    ecimal
    -0.06
    �
    -0.06
    筑
    -0.06
    POSITIVE LOGITS
    _combined
    0.07
    слід
    0.06
     فیلم
    0.06
     durumu
    0.06
    clean
    0.06
    arness
    0.06
    government
    0.06
    oseconds
    0.06
    members
    0.06
    (/*
    0.06
    Act Density 0.025%

    No Known Activations