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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .",
    -0.09
    ”).↵↵
    -0.09
    .",↵
    -0.08
    ”.↵↵
    -0.08
    .",
↵
    -0.08
     Lastly
    -0.08
    .”↵↵
    -0.08
    ”).
    -0.08
     dialogue
    -0.08
    ."),↵
    -0.08
    POSITIVE LOGITS
     ↵
    0.10
     প্রক
    0.08
     Traditionally
    0.08
     doorga
    0.08
     typically
    0.08
      ↵
    0.08
    %↵
    0.08
     Typically
    0.08
     presumably
    0.08
    ：↵
    0.08
    Act Density 0.110%

    No Known Activations