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

    Neuronpedia

    INDEX
    Explanations

    ister

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gradable
    -0.07
    coop
    -0.06
     vegetable
    -0.06
    ROID
    -0.06
     exagger
    -0.06
    ew
    -0.06
    ока
    -0.06
    ashion
    -0.06
    ểm
    -0.06
    うち
    -0.06
    POSITIVE LOGITS
    Interstitial
    0.07
     Hass
    0.06
    ∏
    0.06
    ﻠ
    0.06
     trục
    0.06
     ensl
    0.06
    Brun
    0.06
     reordered
    0.06
    	then
    0.06
    Autoresizing
    0.06
    Act Density 0.002%

    No Known Activations