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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ilian
    -0.07
     overl
    -0.07
    _subs
    -0.06
    Radius
    -0.06
     Hello
    -0.06
    alert
    -0.06
     Tre
    -0.06
     Hick
    -0.06
     selves
    -0.06
    Locker
    -0.06
    POSITIVE LOGITS
     конечно
    0.06
    >&
    0.06
    (GLFW
    0.06
    (Entity
    0.06
     Шев
    0.06
    (metadata
    0.06
     heroic
    0.06
    .providers
    0.06
     Website
    0.06
     vešker
    0.06
    Act Density 0.003%

    No Known Activations