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

    Neuronpedia

    INDEX
    Explanations

    vertical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -town
    -0.07
     Cloud
    -0.07
     лей
    -0.07
    ÜM
    -0.06
     Tonight
    -0.06
     coat
    -0.06
     Want
    -0.06
    agoon
    -0.06
    UGE
    -0.06
     Season
    -0.06
    POSITIVE LOGITS
     vertical
    0.09
     Vertical
    0.08
    Vertical
    0.08
     Horizontal
    0.07
     downwards
    0.07
     خودش
    0.07
     horizontally
    0.07
     downward
    0.07
    vertical
    0.07
     horizontal
    0.07
    Act Density 0.005%

    No Known Activations