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

    Neuronpedia

    INDEX
    Explanations

    press releases

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     blat
    -0.08
    ynec
    -0.07
    ULAR
    -0.07
    >({↵
    -0.07
    טלוויז
    -0.07
    勚
    -0.07
    鼻子
    -0.07
    杙
    -0.07
    舌
    -0.07
    Translated
    -0.07
    POSITIVE LOGITS
     Ammo
    0.07
    嵇
    0.07
     setback
    0.07
    市场需求
    0.07
    .stage
    0.07
     offshore
    0.07
     Security
    0.07
     Apart
    0.07
     requested
    0.07
     fallout
    0.07
    Act Density 0.002%

    No Known Activations