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

    Neuronpedia

    INDEX
    Explanations

    Spanish/Portuguese

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Eine
    -0.07
     Tall
    -0.07
    EEEE
    -0.06
    imore
    -0.06
     References
    -0.06
     Scre
    -0.06
     Russian
    -0.06
     Soviet
    -0.06
     Svět
    -0.06
     painting
    -0.06
    POSITIVE LOGITS
    菌
    0.07
     rm
    0.07
     lacking
    0.07
     ham
    0.07
     backdrop
    0.07
     amongst
    0.06
     �
    0.06
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.06
     pick
    0.06
    [thread
    0.06
    Act Density 0.020%

    No Known Activations