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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     selective
    -0.07
    rition
    -0.07
    矫正
    -0.07
     clearance
    -0.07
     niveau
    -0.07
     Stars
    -0.07
    plitude
    -0.07
     proportions
    -0.07
     Pollution
    -0.07
     texture
    -0.06
    POSITIVE LOGITS
     DEVICE
    0.07
    luet
    0.07
     _______,
    0.07
    released
    0.07
     קטנה
    0.07
     инвестици
    0.06
    十几
    0.06
     does
    0.06
    acb
    0.06
     lässt
    0.06
    Act Density 0.052%

    No Known Activations