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

    Neuronpedia

    INDEX
    Explanations

    yoga poses and flows

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    щения
    -0.07
     Kerr
    -0.07
    userInfo
    -0.07
    鹯
    -0.07
    ("").
    -0.07
    SError
    -0.07
     Biography
    -0.07
    嵛
    -0.06
    撄
    -0.06
    .FromArgb
    -0.06
    POSITIVE LOGITS
     цены
    0.07
    ::↵↵
    0.07
     FEATURES
    0.07
     rule
    0.07
    (properties
    0.06
     privileges
    0.06
    แรง
    0.06
     Rud
    0.06
     أفضل
    0.06
     praise
    0.06
    Act Density 0.021%

    No Known Activations