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

    Neuronpedia

    INDEX
    Explanations

    injecting knowledge or reliability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    balls
    0.38
    gesteld
    0.37
    parts
    0.37
    ribution
    0.36
    iyê
    0.36
    czki
    0.36
    FBSDKError
    0.36
    ther
    0.36
     سلي
    0.36
    荇
    0.36
    POSITIVE LOGITS
     Crib
    0.40
    𝘏
    0.38
    ਸ਼
    0.38
     presso
    0.37
    ड़
    0.37
     کریم
    0.36
     arbitrary
    0.36
    NameTo
    0.35
    Poisson
    0.35
     Couples
    0.35
    Act Density 0.000%

    No Known Activations