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

    Neuronpedia

    INDEX
    Explanations

    legal issues

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     viktigt
    -0.08
     природы
    -0.08
     textured
    -0.07
    tai
    -0.07
     olsun
    -0.07
    :u
    -0.07
     nautical
    -0.07
     valent
    -0.07
     spaced
    -0.07
     commanded
    -0.07
    POSITIVE LOGITS
     unjust
    0.11
     disproportionately
    0.11
     khiến
    0.10
     allegedly
    0.10
     wrongly
    0.10
     unfair
    0.10
     alleges
    0.10
    竟
    0.09
    导致
    0.09
     incorrectly
    0.09
    Act Density 0.164%

    No Known Activations