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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rubbish
    -0.07
    rough
    -0.06
    ，比
    -0.06
     (!((
    -0.06
    	bit
    -0.06
     사이트
    -0.06
    -alpha
    -0.06
     rh
    -0.06
    .Channel
    -0.06
     pe
    -0.06
    POSITIVE LOGITS
     Ritual
    0.08
     Islamic
    0.07
    悪
    0.07
    ignite
    0.07
    StyleSheet
    0.07
    al
    0.06
     ])↵↵
    0.06
     Bliss
    0.06
    Recipes
    0.06
    icious
    0.06
    Act Density 0.001%

    No Known Activations