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

    Neuronpedia

    INDEX
    Explanations

    ild

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [position
    -0.07
     essere
    -0.06
    وقع
    -0.06
    utex
    -0.06
    Versions
    -0.06
    emory
    -0.06
    )..
    -0.06
     responsibility
    -0.06
     Acting
    -0.06
     Split
    -0.06
    POSITIVE LOGITS
     mild
    0.21
     Mild
    0.14
     mildly
    0.11
    7
    0.07
    �
    0.07
    ild
    0.07
    LD
    0.07
     bald
    0.07
    BSD
    0.07
    415
    0.07
    Act Density 0.004%

    No Known Activations