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

    Neuronpedia

    INDEX
    Explanations

    questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    REAT
    -0.07
     Signing
    -0.06
     Gut
    -0.06
     therapist
    -0.06
     Balanced
    -0.06
    '(
    -0.06
     Solutions
    -0.06
     trav
    -0.06
     guerra
    -0.06
     GET
    -0.06
    POSITIVE LOGITS
     нор
    0.07
    -complete
    0.06
    视频
    0.06
     misrepresented
    0.06
     더욱
    0.06
     β
    0.06
    (
↵
    0.06
    aq
    0.06
     Optionally
    0.06
     bola
    0.06
    Act Density 0.191%

    No Known Activations