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

    Neuronpedia

    INDEX
    Explanations

    contradicting guidelines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     geçiril
    -0.09
     Cin
    -0.09
    .array
    -0.08
     lágrimas
    -0.08
     __________________
    -0.08
     Quinta
    -0.08
    Cin
    -0.08
     Odd
    -0.08
    _ARRAY
    -0.08
    中央
    -0.08
    POSITIVE LOGITS
     ممكن
    0.09
    قت
    0.09
    putable
    0.08
     disclaim
    0.08
     ales
    0.08
     مفهوم
    0.08
    -safe
    0.08
     delicate
    0.08
     handbag
    0.08
     ๆ
    0.08
    Act Density 0.001%

    No Known Activations