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

    Neuronpedia

    INDEX
    Explanations

    morb

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    軟
    -0.07
    rient
    -0.06
    夫
    -0.06
    _RESET
    -0.06
    gay
    -0.06
     Powder
    -0.06
    Роз
    -0.06
     finished
    -0.06
    Tabs
    -0.06
    .routes
    -0.06
    POSITIVE LOGITS
     chiế
    0.07
     wasm
    0.07
    .vm
    0.07
     Πολι
    0.07
     diagn
    0.07
     \
↵
    0.07
     exemplo
    0.06
    ..........
    0.06
    (or
    0.06
     Biblical
    0.06
    Act Density 0.035%

    No Known Activations