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

    Neuronpedia

    INDEX
    Explanations

    dynamic, romantic, silent, cyclic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    सादर
    0.56
    ifiably
    0.46
    方
    0.46
    𝚓
    0.46
    czki
    0.46
    ूठी
    0.44
    presso
    0.44
     blistering
    0.44
     kilometers
    0.43
    方的
    0.43
    POSITIVE LOGITS
    ^{\
    0.47
     IN
    0.46
     manifest
    0.46
     оф
    0.45
     Seç
    0.45
     nào
    0.44
     BAS
    0.44
    ^{-
    0.43
     DID
    0.42
     -
    0.42
    Act Density 0.000%

    No Known Activations