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

    Neuronpedia

    INDEX
    Explanations

    data storage tiers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Handlung
    -0.08
     Blockly
    -0.08
    _menu
    -0.08
    Mw
    -0.08
     شخصیت
    -0.08
    _button
    -0.08
    Nep
    -0.08
    _login
    -0.08
     npe
    -0.07
    Mage
    -0.07
    POSITIVE LOGITS
     storage
    0.16
     opslag
    0.16
     armazenamento
    0.15
     almacenamiento
    0.15
    .Storage
    0.15
    .storage
    0.15
     архив
    0.15
     хранения
    0.15
    (storage
    0.15
    -storage
    0.15
    Act Density 0.013%

    No Known Activations