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

    Neuronpedia

    INDEX
    Explanations

    glistening ancient rose red

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     osoba
    0.59
     motivación
    0.57
     ajuda
    0.56
     hairstyle
    0.54
     snacks
    0.54
    ‼️
    0.53
     alleine
    0.52
     inability
    0.52
     relatable
    0.50
    個人
    0.49
    POSITIVE LOGITS
     gleaming
    0.86
     glistening
    0.68
     shimmering
    0.59
     glittering
    0.57
    clustering
    0.56
     billowing
    0.55
     flung
    0.54
     sleek
    0.54
     jost
    0.52
    compact
    0.52
    Act Density 0.060%

    No Known Activations