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

    Neuronpedia

    INDEX
    Explanations

    usage instructions

    np_max-act · gemini-2.0-flash

    This neuron selectively activates on occurrences of the preposition “in.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ابد
    -0.07
    ｊ
    -0.06
    Friday
    -0.06
    .travel
    -0.06
    nesia
    -0.06
     tougher
    -0.06
     Plenty
    -0.06
    _QUESTION
    -0.06
    řit
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     faithful
    0.07
    _timeline
    0.07
     Ultimate
    0.07
     공
    0.06
     bức
    0.06
     accuse
    0.06
    uted
    0.06
    行政
    0.06
    aled
    0.06
    ordial
    0.06
    Act Density 0.078%

    No Known Activations