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

    Neuronpedia

    INDEX
    Explanations

    Methods

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cunning
    -0.07
     pérd
    -0.07
     trumpet
    -0.07
     telegram
    -0.07
    Mongo
    -0.07
    -grand
    -0.07
     тому
    -0.07
     '">'
    -0.07
    ByUsername
    -0.07
    眼里
    -0.07
    POSITIVE LOGITS
     Let
    0.07
    姞
    0.07
    節
    0.07
    Ө
    0.07
    IELDS
    0.07
     saturation
    0.07
     Sh
    0.07
    괴
    0.07
    湲
    0.07
     الن
    0.07
    Act Density 0.000%

    No Known Activations