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

    Neuronpedia

    INDEX
    Explanations

    Smallness

    np_max-act · gemini-2.0-flash

    The neuron activates on terms that denote small, measured quantities or frequencies (e.g. “small,” “frequent,” “sips,” “amounts”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    تور
    -0.06
     accommodation
    -0.06
     解
    -0.06
     Panels
    -0.06
     therein
    -0.06
    262
    -0.06
     winner
    -0.06
     Triangle
    -0.06
    =root
    -0.06
    .$$
    -0.06
    POSITIVE LOGITS
     суспіль
    0.07
    emple
    0.07
     SCE
    0.07
    ulates
    0.06
    .goto
    0.06
    �
    0.06
     Quận
    0.06
    xi
    0.06
     dab
    0.06
     вспом
    0.06
    Act Density 0.017%

    No Known Activations