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

    Neuronpedia

    INDEX
    Explanations

    Math and geometry

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     തൊഴില
    -0.10
     употреб
    -0.09
     Jinping
    -0.09
     pekerjaan
    -0.09
     民
    -0.08
     outage
    -0.08
     moyo
    -0.08
     भर्ती
    -0.08
    �
    -0.08
     福建
    -0.08
    POSITIVE LOGITS
    äs
    0.09
     talk
    0.08
    Talk
    0.08
    .at
    0.08
     talks
    0.08
     Talks
    0.08
    Broadcast
    0.07
    _lines
    0.07
     interplay
    0.07
     collider
    0.07
    Act Density 0.019%

    No Known Activations