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

    Neuronpedia

    INDEX
    Explanations

    ` ` to `.`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     เสียง
    0.55
     божомолу
    0.52
     aurez
    0.51
     haue
    0.50
     समावेश
    0.50
     एव
    0.49
     opposes
    0.49
     συνα
    0.49
    లతో
    0.49
     उंची
    0.49
    POSITIVE LOGITS
    وب
    0.50
    e
    0.47
    ⁀
    0.46
    completed
    0.43
    ار
    0.42
    力
    0.42
    Status
    0.41
    Does
    0.41
    都
    0.41
     pyt
    0.40
    Act Density 0.001%

    No Known Activations