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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Assignment
    -0.08
    lem
    -0.07
    Neo
    -0.07
     Sac
    -0.07
     FileStream
    -0.06
    GameOver
    -0.06
    Faculty
    -0.06
                            
↵
    -0.06
     recognize
    -0.06
    Ά
    -0.06
    POSITIVE LOGITS
     TU
    0.08
    IEW
    0.07
    IMIT
    0.07
     CUT
    0.07
    IKE
    0.07
    coni
    0.06
    ":"'
    0.06
    otine
    0.06
    -gun
    0.06
     spa
    0.06
    Act Density 0.035%

    No Known Activations