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

    Neuronpedia

    INDEX
    Explanations

    toast and toaster

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     getline
    0.43
    ステム
    0.39
     dimers
    0.38
     juin
    0.38
     luoghi
    0.38
     needle
    0.38
     upstream
    0.38
     پڑھیئے
    0.37
    尿
    0.37
     STEM
    0.37
    POSITIVE LOGITS
     toast
    1.28
     Toast
    1.20
    🍞
    1.16
    Toast
    1.13
    toast
    1.13
     toasted
    1.11
     toasts
    1.11
     toaster
    1.08
     хле
    1.05
     bread
    1.03
    Act Density 0.010%

    No Known Activations