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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Descending
    -0.08
     Freak
    -0.07
     investigation
    -0.07
     некоторых
    -0.06
    �
    -0.06
    SetTitle
    -0.06
     produits
    -0.06
    Paris
    -0.06
    imonials
    -0.06
    igor
    -0.06
    POSITIVE LOGITS
    .viewer
    0.06
     js
    0.06
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.06
    脂
    0.06
    	Default
    0.06
     administr
    0.06
     از
    0.06
     бог
    0.06
    olución
    0.06
     ＞
    0.06
    Act Density 0.036%

    No Known Activations