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

    Neuronpedia

    INDEX
    Explanations

    Crime and punishment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -readable
    -0.08
     gratis
    -0.08
    /mobile
    -0.08
     மெ
    -0.08
     cadeau
    -0.08
    مل
    -0.08
    -envelope
    -0.08
     sustaining
    -0.08
    Mood
    -0.08
     brunch
    -0.08
    POSITIVE LOGITS
     sensational
    0.09
    杀
    0.09
     pessim
    0.09
     punitive
    0.09
     paranoid
    0.09
     condemnation
    0.09
     grotes
    0.08
     killings
    0.08
     қауіп
    0.08
     hostility
    0.08
    Act Density 0.169%

    No Known Activations