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

    Neuronpedia

    INDEX
    Explanations

    you need or want

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     आपण
    0.45
    الو
    0.39
    ग्राहक
    0.39
     hogi
    0.38
     stakes
    0.38
     poma
    0.38
     frontiers
    0.37
     dle
    0.37
     Seeking
    0.36
     descansar
    0.36
    POSITIVE LOGITS
     want
    0.67
     encountered
    0.65
     obtained
    0.59
     encounter
    0.58
     have
    0.56
    有一个
    0.55
     intend
    0.54
     forgot
    0.53
     suspect
    0.52
     wanted
    0.51
    Act Density 0.022%

    No Known Activations