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

    Neuronpedia

    INDEX
    Explanations

    README files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Highlander
    0.44
    顎
    0.44
     vacuo
    0.42
    視覺
    0.42
    翮
    0.42
     hoist
    0.41
    售价
    0.41
     prix
    0.41
     academics
    0.41
     জেল
    0.41
    POSITIVE LOGITS
    ltre
    0.43
    rimi
    0.43
    atschapp
    0.41
    iddel
    0.41
     ملے
    0.40
    olim
    0.38
     profunda
    0.38
    وني
    0.37
    riques
    0.37
    ahui
    0.37
    Act Density 0.009%

    No Known Activations