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

    Neuronpedia

    INDEX
    Explanations

    https

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -minded
    -0.07
     چشم
    -0.07
    Cnt
    -0.06
    독
    -0.06
     apologies
    -0.06
    儀
    -0.06
     considers
    -0.06
    تل
    -0.06
     اهم
    -0.06
     وال
    -0.06
    POSITIVE LOGITS
     ListBox
    0.07
    =[]
↵
    0.07
     �
    0.07
     Jes
    0.07
    ↵↵↵↵↵↵↵
    0.07
    iju
    0.07
     disorder
    0.07
     tarif
    0.07
    (status
    0.07
    }'↵
    0.07
    Act Density 0.003%

    No Known Activations