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

    Neuronpedia

    INDEX
    Explanations

    3

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Project
    -0.07
     compare
    -0.06
    Community
    -0.06
    Again
    -0.06
    Ju
    -0.06
    ائم
    -0.06
    semblies
    -0.06
     
    -0.06
    IRECTION
    -0.06
     whip
    -0.06
    POSITIVE LOGITS
     sexy
    0.06
     annot
    0.06
    .fixed
    0.06
     left
    0.06
    .Invariant
    0.06
    	left
    0.06
     ©
    0.06
     [.
    0.06
    ,obj
    0.06
    _arrow
    0.06
    Act Density 0.001%

    No Known Activations