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
     pemb
    -0.06
     आख
    -0.06
    /respond
    -0.06
     Alman
    -0.06
    ่าท
    -0.06
     Yunan
    -0.06
     protagonists
    -0.06
     Temmuz
    -0.06
     descri
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    NSMutableArray
    0.07
    ↵        
↵
    0.07
    Ξ
    0.06
    sending
    0.06
     projectile
    0.06
     ↵  ↵
    0.06
    NSMutableDictionary
    0.06
    blank
    0.06
    ・・・↵↵
    0.06
    $$
    0.06
    Act Density 0.192%

    No Known Activations