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

    Neuronpedia

    INDEX
    Explanations

    whose

    np_max-act · gemini-2.0-flash

    This neuron activates on the relative possessive pronoun “whose.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ail
    -0.08
     it
    -0.07
     they
    -0.07
    I
    -0.07
    It
    -0.07
     میدان
    -0.06
    ia
    -0.06
    ']}}</
    -0.06
    _apply
    -0.06
    it
    -0.06
    POSITIVE LOGITS
     whose
    0.17
    whose
    0.15
     Who
    0.07
    자의
    0.07
    (named
    0.07
     Your
    0.07
     DOE
    0.07
    ，把
    0.07
     jehož
    0.07
     who
    0.07
    Act Density 0.008%

    No Known Activations