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

    Neuronpedia

    INDEX
    Explanations

    in role

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    },↵↵
    -0.07
    "h
    -0.07
     beds
    -0.07
     dny
    -0.07
     geek
    -0.06
    [
    -0.06
    _ok
    -0.06
    ↵   ↵
    -0.06
    Et
    -0.06
    Care
    -0.06
    POSITIVE LOGITS
     Pompeo
    0.06
    いや
    0.06
    cház
    0.06
    .rd
    0.06
    esan
    0.06
    λα
    0.06
    urbation
    0.06
     ανα
    0.06
    、それ
    0.06
    -low
    0.06
    Act Density 0.160%

    No Known Activations