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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    user input markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     HasFactory
    -0.77
    AndEndTag
    -0.75
    SequentialGroup
    -0.65
     createState
    -0.64
     JpaRepository
    -0.63
    setArguments
    -0.60
     חיצוניים
    -0.60
     Exacts
    -0.59
     témoig
    -0.58
     Audiodateien
    -0.57
    POSITIVE LOGITS
    .
    0.47
     CLASS
    0.36
    <bos>
    0.36
     Des
    0.36
     \
    0.35
     Lis
    0.35
     To
    0.35
     re
    0.35
     IS
    0.33
     Ci
    0.33
    Act Density 0.000%

    No Known Activations