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

    Neuronpedia

    INDEX
    Explanations

    &

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    やる
    -0.07
     ناح
    -0.06
    寄
    -0.06
    �
    -0.06
    क
    -0.06
     раді
    -0.06
     quoi
    -0.06
     keeping
    -0.06
     wissen
    -0.06
     prov
    -0.05
    POSITIVE LOGITS
     δι
    0.07
     intermittent
    0.07
    ное
    0.07
     empowerment
    0.07
     Milano
    0.07
    =random
    0.07
    )'],↵
    0.06
    ENTE
    0.06
     regularly
    0.06
     Graphics
    0.06
    Act Density 0.001%

    No Known Activations