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

    Neuronpedia

    INDEX
    Explanations

    Directional movement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _corpus
    -0.08
     aşırı
    -0.07
     anybody
    -0.07
    'D
    -0.07
    νονται
    -0.07
     stating
    -0.07
    Lastly
    -0.07
    Không
    -0.06
    ług
    -0.06
    ічного
    -0.06
    POSITIVE LOGITS
     down
    0.07
     gratitude
    0.07
     UP
    0.07
     Down
    0.07
    Michael
    0.06
     명
    0.06
     Portugal
    0.06
    PLIER
    0.06
     deltaY
    0.06
     McCorm
    0.06
    Act Density 0.031%

    No Known Activations