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

    Neuronpedia

    INDEX
    Explanations

    benefit or harm

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    agate
    -0.07
     AUT
    -0.06
     Παν
    -0.06
    "After
    -0.06
    HU
    -0.06
     COMM
    -0.06
     Posts
    -0.06
     Charl
    -0.06
     Intent
    -0.06
    iox
    -0.06
    POSITIVE LOGITS
     Bordeaux
    0.07
     категор
    0.07
    晶
    0.07
    tainment
    0.07
    unprocessable
    0.07
     저장
    0.06
    NewUrlParser
    0.06
    ora
    0.06
    595
    0.06
     sky
    0.06
    Act Density 0.007%

    No Known Activations