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

    Neuronpedia

    INDEX
    Explanations

    references to content and its attributes in data structures or programming contexts

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

    content identifier or length

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Infórmanos
    -0.62
    DockStyle
    -0.61
     ब्रेकडाउन
    -0.58
    mains
    -0.54
    BufferException
    -0.53
    期刊论文
    -0.52
    ported
    -0.51
    Personendaten
    -0.50
    CodedInputStream
    -0.49
     kasarigan
    -0.49
    POSITIVE LOGITS
     sanitarias
    0.37
     locaux
    0.36
     connaissances
    0.35
     classiques
    0.35
    HttpPut
    0.34
     lettore
    0.34
     WORD
    0.33
    guiente
    0.33
     word
    0.33
     obsah
    0.32
    Act Density 0.012%

    No Known Activations