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

    Neuronpedia

    INDEX
    Explanations

    Sight or seeing

    np_max-act · gemini-2.0-flash

    The neuron activates on the word “sight” (and its close variant “seeing”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     adding
    -0.07
    ran
    -0.07
    .epam
    -0.07
     randomly
    -0.07
    Bezier
    -0.07
     radical
    -0.07
     وكان
    -0.07
     gradual
    -0.06
    .PARAM
    -0.06
    Album
    -0.06
    POSITIVE LOGITS
     sight
    0.14
     Sight
    0.11
    ight
    0.09
    IGHT
    0.09
     Vista
    0.08
    ikt
    0.08
     �
    0.07
     sights
    0.07
    sworth
    0.07
     MST
    0.07
    Act Density 0.009%

    No Known Activations