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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lights
    -0.07
    MN
    -0.07
    -lined
    -0.06
    言い
    -0.06
     Shore
    -0.06
    办
    -0.06
    Rev
    -0.06
     publik
    -0.06
     LF
    -0.06
     prot
    -0.06
    POSITIVE LOGITS
    (DWORD
    0.06
    esidir
    0.06
    ़क
    0.06
     ulaş
    0.06
    exterity
    0.06
    ワー
    0.06
    "]:
    0.06
    ριος
    0.06
     ~=
    0.06
    .CommandType
    0.06
    Act Density 0.001%

    No Known Activations