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

    Neuronpedia

    INDEX
    Explanations

    numerical values related to data and statistics

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

    user index

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aliens
    -0.38
    bondale
    -0.33
     sticker
    -0.32
    
    -0.32
     Monuments
    -0.32
    onAttach
    -0.31
     Mind
    -0.31
     alien
    -0.31
    помним
    -0.31
     Document
    -0.31
    POSITIVE LOGITS
    rungsseite
    0.64
    +#+#
    0.63
    AndEndTag
    0.59
    Архівовано
    0.58
    ніципалі
    0.57
    Източници
    0.54
     invokingState
    0.54
    Rujuakan
    0.53
    bibnamefont
    0.51
    oneofs
    0.49
    Act Density 0.035%

    No Known Activations