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

    Neuronpedia

    INDEX
    Explanations

    air bubbles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     diverses
    0.62
     condol
    0.61
     versch
    0.57
     intranet
    0.57
     disparity
    0.56
     intellectually
    0.55
     malice
    0.55
     paycheck
    0.54
     más
    0.54
     ligand
    0.54
    POSITIVE LOGITS
    bubbles
    0.57
    ref
    0.57
    8
    0.56
    TR
    0.56
    роди
    0.55
    IND
    0.55
    p
    0.55
    bubble
    0.54
    ter
    0.53
    Bubble
    0.53
    Act Density 0.014%

    No Known Activations