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

    Neuronpedia

    INDEX
    Explanations

    when

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    自然灾害
    -0.08
     bulunmaktadır
    -0.08
    al
    -0.08
    ar
    -0.08
     submissions
    -0.07
    Americans
    -0.07
    알
    -0.07
    cribes
    -0.07
     You
    -0.07
     you
    -0.07
    POSITIVE LOGITS
     when
    0.09
    kin
    0.07
    	when
    0.07
    YNAM
    0.07
    .jwt
    0.07
    ⓗ
    0.06
    غل
    0.06
     להשתמש
    0.06
     Hyde
    0.06
    到时候
    0.06
    Act Density 0.176%

    No Known Activations