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

    Neuronpedia

    INDEX
    Explanations

    key identifiers or headings in structured documents

    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
    AndEndTag
    -0.69
    ロウィン
    -0.66
     itſelf
    -0.63
     estekak
    -0.63
     MutableLiveData
    -0.61
     newData
    -0.60
    <unused41>
    -0.60
    <unused52>
    -0.60
    <unused17>
    -0.60
    <pad>
    -0.60
    POSITIVE LOGITS
    ConstraintMaker
    0.36
    .*")]
    0.34
    VersionUID
    0.27
     générations
    0.27
     تضيفلها
    0.27
    protoimpl
    0.26
    iseite
    0.25
    Diweddarwch
    0.25
    FAILURE
    0.24
    qxd
    0.24
    Act Density 0.000%

    No Known Activations