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

    Neuronpedia

    INDEX
    Explanations

    Java import statements related to various utility and logging libraries

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

    <start_of_turn>user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    matchCondition
    -0.44
    Blockly
    -0.40
    TypedDataSet
    -0.35
    <eos>
    -0.35
    StringCopy
    -0.33
    ⅘
    -0.32
    WriteBarrier
    -0.31
    stdc
    -0.31
    Personendaten
    -0.31
    bewerken
    -0.30
    POSITIVE LOGITS
     zoude
    0.61
     mijne
    0.59
     zijne
    0.58
     desmotivaciones
    0.57
    majánló
    0.57
     ſeinen
    0.56
     CURIAM
    0.56
     Geiſt
    0.54
    citroën
    0.54
     Autorizaciones
    0.53
    Act Density 0.028%

    No Known Activations