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

    Neuronpedia

    INDEX
    Explanations

    creating lists or crafting items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rinsic
    1.64
     Leop
    1.41
    __(/*!
    1.37
     deficient
    1.35
    <unused437>
    1.34
    funct
    1.34
     multifunctional
    1.33
     sexu
    1.33
    <unused508>
    1.33
    žas
    1.32
    POSITIVE LOGITS
    www
    1.25
    Word
    1.12
    Message
    1.09
     www
    1.09
    (
    1.02
    ↵↵
    0.98
    put
    0.97
    Check
    0.97
    Im
    0.96
    A
    0.96
    Act Density 0.151%

    No Known Activations