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

    Neuronpedia

    INDEX
    Explanations

    look

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of the word “look” (and its forms “looks”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _pin
    -0.07
    λί
    -0.06
     denně
    -0.06
     málo
    -0.06
    ById
    -0.06
    ân
    -0.06
    ĩnh
    -0.06
    cole
    -0.06
    upa
    -0.06
     yanında
    -0.06
    POSITIVE LOGITS
     look
    0.08
     реак
    0.07
     locking
    0.07
     remarked
    0.07
     Looks
    0.07
     record
    0.07
     hacking
    0.06
     hepatitis
    0.06
     OCC
    0.06
    .Dec
    0.06
    Act Density 0.010%

    No Known Activations