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
    longleftrightarrow
    -0.07
    ‌کنند
    -0.07
     isAuthenticated
    -0.07
    Sender
    -0.06
    遗
    -0.06
    ，此
    -0.06
    达
    -0.06
     orthogonal
    -0.06
     expires
    -0.06
     požad
    -0.06
    POSITIVE LOGITS
    LEM
    0.07
     Walker
    0.07
     =============================================================================↵
    0.07
    agg
    0.07
    ラス
    0.07
     united
    0.07
     gums
    0.06
     ate
    0.06
    	  ↵
    0.06
     setInput
    0.06
    Act Density 0.051%

    No Known Activations