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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    The neuron primarily detects the English “to” particle (as in the infinitive marker).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     unprotected
    -0.07
    Ser
    -0.06
     Lan
    -0.06
    ization
    -0.06
    isation
    -0.06
     europé
    -0.06
    орож
    -0.06
    اح
    -0.06
     '&
    -0.05
    ุง
    -0.05
    POSITIVE LOGITS
     TRUE
    0.07
    getElement
    0.07
     کنار
    0.07
     Perfect
    0.07
    ’de
    0.07
     Tmin
    0.06
     *_
    0.06
    _leader
    0.06
     nevě
    0.06
     чин
    0.06
    Act Density 0.044%

    No Known Activations