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

    Neuronpedia

    INDEX
    Explanations

    comparative attributes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    trib
    -0.08
     Whe
    -0.07
     quaternion
    -0.07
     dih
    -0.07
     Autón
    -0.07
     francés
    -0.07
     Rab
    -0.07
     hydration
    -0.07
    ڪ
    -0.07
     autoc
    -0.07
    POSITIVE LOGITS
     ranked
    0.12
     ranking
    0.12
    -ranking
    0.11
     rankings
    0.11
    Ranking
    0.11
    -ranked
    0.11
     Ranking
    0.11
     comparative
    0.11
     Ranked
    0.11
     Rankings
    0.11
    Act Density 0.026%

    No Known Activations