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

    Neuronpedia

    INDEX
    Explanations

    poetic/descriptive texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    活动
    -0.08
     ji
    -0.07
    效
    -0.07
    -0.07
     Opportunities
    -0.06
    طار
    -0.06
    �
    -0.06
    견
    -0.06
     समस
    -0.06
     INSTANCE
    -0.06
    POSITIVE LOGITS
     طرح
    0.06
    (panel
    0.06
     silent
    0.06
    entimes
    0.06
    "On
    0.06
    .RowStyles
    0.06
     ….
    0.06
     Lakers
    0.06
    .normalize
    0.06
    eca
    0.05
    Act Density 0.104%

    No Known Activations