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

    Neuronpedia

    INDEX
    Explanations

    conversational phrases and transitions in discussions about processes and conditions

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

    programming language fragments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     '{@
    -0.33
    oredCriteria
    -0.32
    föl
    -0.32
    IsMutable
    -0.32
    BufferException
    -0.29
    Jereo
    -0.29
     iterator
    -0.29
     abiti
    -0.29
    lük
    -0.28
    LEncoder
    -0.28
    POSITIVE LOGITS
    antaranya
    0.59
     antaranya
    0.54
    AddTagHelper
    0.54
     całość
    0.50
     فريبيس
    0.50
    WriteTagHelper
    0.49
     initComponents
    0.49
    ándolo
    0.49
    éndolo
    0.48
    SourceChecksum
    0.48
    Act Density 0.421%

    No Known Activations