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

    Neuronpedia

    INDEX
    Explanations

    ‐

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     BALL
    -0.07
     Facilities
    -0.06
    .tools
    -0.06
    .styles
    -0.06
     Fan
    -0.06
     Monitoring
    -0.06
    Seen
    -0.06
     Calvin
    -0.06
    Finished
    -0.06
    .annot
    -0.06
    POSITIVE LOGITS
    eated
    0.07
    ucción
    0.06
    hips
    0.06
    مق
    0.06
    ahl
    0.06
    ��글
    0.06
    .ISupportInitialize
    0.06
    currentState
    0.06
    pairs
    0.06
     बच
    0.06
    Act Density 0.006%

    No Known Activations