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

    Neuronpedia

    INDEX
    Explanations

    Math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Federation
    -0.07
    .directive
    -0.07
    -ब
    -0.07
    اشین
    -0.07
    imen
    -0.06
    fr
    -0.06
    Ｋ
    -0.06
    (messages
    -0.06
    immers
    -0.06
     журн
    -0.06
    POSITIVE LOGITS
     ευ
    0.07
     Emma
    0.06
     ((
    0.06
    >("
    0.06
     доб
    0.06
     AGAIN
    0.06
     selon
    0.06
    .u
    0.06
     valleys
    0.06
     avant
    0.06
    Act Density 0.004%

    No Known Activations