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

    Neuronpedia

    INDEX
    Explanations

    >

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     하
    -0.07
    _RS
    -0.06
     trung
    -0.06
    vertisement
    -0.06
     stitches
    -0.06
    uning
    -0.06
    .truth
    -0.06
    _parameters
    -0.06
    绝
    -0.06
     chromium
    -0.06
    POSITIVE LOGITS
     entra
    0.07
    }*/↵↵
    0.07
     elle
    0.06
     подт
    0.06
     serialize
    0.06
    ает
    0.06
    BLE
    0.06
     gigg
    0.06
    корист
    0.06
     są
    0.06
    Act Density 0.015%

    No Known Activations