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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     války
    -0.08
     SQUARE
    -0.07
    .Av
    -0.07
     namedtuple
    -0.07
     Brisbane
    -0.06
    「
    -0.06
     right
    -0.06
     summon
    -0.06
     ​
    -0.06
    -го
    -0.06
    POSITIVE LOGITS
     Redistributions
    0.07
     ohne
    0.06
    (火
    0.06
    dfs
    0.06
    .Note
    0.06
    링
    0.06
     prer
    0.06
    (er
    0.06
    API
    0.06
     найбіль
    0.06
    Act Density 0.022%

    No Known Activations