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

    Neuronpedia

    INDEX
    Explanations

    network

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _fe
    -0.07
     nút
    -0.07
     lief
    -0.06
    ъем
    -0.06
    馬
    -0.06
     Stef
    -0.06
    ienia
    -0.06
     balancing
    -0.06
    Carl
    -0.06
    Law
    -0.06
    POSITIVE LOGITS
    Dur
    0.07
     zg
    0.06
     Sask
    0.06
     Ducks
    0.06
     sorun
    0.06
    ´
    0.06
     والس
    0.06
     rodz
    0.06
     blogs
    0.06
    teen
    0.06
    Act Density 0.014%

    No Known Activations