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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    磨损
    -0.07
    不懈
    -0.07
    	fn
    -0.07
     dedication
    -0.07
    ample
    -0.06
    증
    -0.06
    .sigmoid
    -0.06
     Alonso
    -0.06
    蠡
    -0.06
    💿
    -0.06
    POSITIVE LOGITS
    TOT
    0.07
     underworld
    0.07
    Generally
    0.07
    콤
    0.07
    —or
    0.07
    黄瓜
    0.07
    _CONTROLLER
    0.07
    presentation
    0.07
    OTT
    0.06
    .sav
    0.06
    Act Density 0.001%

    No Known Activations