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

    Neuronpedia

    INDEX
    Explanations

    travel guides

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     compositions
    -0.07
    intro
    -0.07
    _language
    -0.07
     unilateral
    -0.07
     camping
    -0.07
    켜
    -0.07
    ыми
    -0.07
    _linear
    -0.07
     інститут
    -0.07
     mirrors
    -0.06
    POSITIVE LOGITS
     آسی
    0.07
    (fout
    0.06
     afterEach
    0.06
     NSStringFromClass
    0.06
     उसक
    0.06
     Oliver
    0.06
     bát
    0.06
     attravers
    0.06
     unsus
    0.06
     hemp
    0.06
    Act Density 0.132%

    No Known Activations