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

    Neuronpedia

    INDEX
    Explanations

    be

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     работе
    -0.08
     mio
    -0.06
    $message
    -0.06
    _world
    -0.06
     tiền
    -0.06
     води
    -0.06
     Draco
    -0.06
     skept
    -0.06
     cru
    -0.06
     Θ
    -0.06
    POSITIVE LOGITS
     sparks
    0.08
     Personen
    0.07
     ''↵↵
    0.07
    styleType
    0.07
    _FOCUS
    0.07
    व
    0.07
    quoted
    0.06
    향
    0.06
    Crow
    0.06
    <Component
    0.06
    Act Density 0.071%

    No Known Activations