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

    Neuronpedia

    INDEX
    Explanations

    code block terminators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     permangan
    0.33
     spoons
    0.32
     thịt
    0.32
    นา
    0.31
     flasks
    0.30
     carc
    0.30
     vodka
    0.30
     bisc
    0.29
     microbiome
    0.29
     marshmallows
    0.29
    POSITIVE LOGITS
    end
    0.35
       
    0.35
    ↵↵↵↵
    0.33
        
    0.33
    bibfield
    0.33
    ual
    0.33
         
    0.32
    ↵↵↵
    0.32
    else
    0.31
    dding
    0.31
    Act Density 0.216%

    No Known Activations