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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PERFORMANCE
    -0.07
    resas
    -0.06
    >r
    -0.06
    ワー
    -0.06
     özellikle
    -0.06
     назнач
    -0.06
     puedes
    -0.06
    علوم
    -0.06
     ткани
    -0.06
     ENABLE
    -0.06
    POSITIVE LOGITS
     Library
    0.06
     fragments
    0.06
     outlet
    0.06
     filtered
    0.06
     appart
    0.06
     ontvang
    0.06
    _problem
    0.06
    errick
    0.06
     kernel
    0.06
     случаях
    0.06
    Act Density 0.001%

    No Known Activations