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

    Neuronpedia

    INDEX
    Explanations

    super power, VR, bred

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ه
    0.50
    ה
    0.47
    ів
    0.47
    ్
    0.46
    𝗲
    0.46
    ার্থী
    0.46
    ن
    0.46
     сот
    0.44
    ر
    0.44
     ότι
    0.43
    POSITIVE LOGITS
     animales
    0.49
     nieder
    0.47
     polygonal
    0.47
     Bolog
    0.47
     Madeira
    0.47
     Duf
    0.47
     Ferté
    0.47
     anatom
    0.46
     Oiseau
    0.46
     cumplir
    0.46
    Act Density 0.005%

    No Known Activations