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

    Neuronpedia

    INDEX
    Explanations

    station

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    蛲
    -0.07
     tempted
    -0.07
    ustain
    -0.07
    ⵍ
    -0.07
     cannabis
    -0.07
    截至
    -0.07
     scl
    -0.06
    _module
    -0.06
     gating
    -0.06
     vortex
    -0.06
    POSITIVE LOGITS
    _ASYNC
    0.07
    印象深刻
    0.07
    昃
    0.07
     WELL
    0.07
    㙍
    0.06
     Rent
    0.06
    前所
    0.06
    这样一来
    0.06
     העיק
    0.06
    orum
    0.06
    Act Density 0.020%

    No Known Activations