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

    Neuronpedia

    INDEX
    Explanations

    conversations and emotional responses related to identity and acceptance

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

    reporting findings or observations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ormais
    -0.50
     Mentions
    -0.47
     ambition
    -0.43
    ствий
    -0.42
    ModelSerializer
    -0.42
    Cyfeiriadau
    -0.42
    Routine
    -0.42
    淳
    -0.42
    geoning
    -0.41
    関連記事
    -0.40
    POSITIVE LOGITS
     Савезне
    0.47
     simplifié
    0.44
     Infórmanos
    0.44
    :✨
    0.42
    BufferException
    0.41
     noDo
    0.41
     myself
    0.40
    matchCondition
    0.39
    ьаж
    0.39
    dart
    0.37
    Act Density 0.028%

    No Known Activations