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

    Neuronpedia

    INDEX
    Explanations

    derivatives and equations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     পাশাপাশি
    -0.08
     thời
    -0.08
     trị
    -0.07
     stretch
    -0.07
     reconnu
    -0.07
    িটির
    -0.07
     válida
    -0.07
     আমরা
    -0.07
     it'll
    -0.07
    িটি
    -0.07
    POSITIVE LOGITS
     makk
    0.08
    Sab
    0.08
     habt
    0.08
     distracted
    0.08
    Has
    0.08
     zabo
    0.08
    (cancel
    0.08
    eds
    0.08
     liefst
    0.08
    (GET
    0.08
    Act Density 0.003%

    No Known Activations