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

    Neuronpedia

    INDEX
    Explanations

    raise, open

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ンド
    -0.06
     Yours
    -0.06
     };
    -0.06
     were
    -0.06
    ovies
    -0.06
     πρό
    -0.06
    chin
    -0.06
    μές
    -0.05
    ією
    -0.05
     NSK
    -0.05
    POSITIVE LOGITS
     Elevated
    0.07
    FileSystem
    0.07
     Future
    0.06
     haunt
    0.06
    .failed
    0.06
     Зап
    0.06
    Ye
    0.06
    enes
    0.06
    Divider
    0.06
     знову
    0.06
    Act Density 0.053%

    No Known Activations