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

    Neuronpedia

    INDEX
    Explanations

    the presence of the word "im" and related identifiers in various contexts

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

    in our case

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     arbit
    -0.49
     juſ
    -0.48
    TagMode
    -0.44
    sentence
    -0.38
     ſol
    -0.38
    documentElement
    -0.38
    ########.
    -0.37
     perfiles
    -0.35
     ſtand
    -0.35
     perſ
    -0.35
    POSITIVE LOGITS
     нас
    0.77
     पास
    0.60
    UnusedPrivate
    0.60
     Вас
    0.57
     الرياضيه
    0.53
     Taktlose
    0.53
    Там
    0.51
     там
    0.51
    principalTable
    0.50
     вас
    0.50
    Act Density 0.003%

    No Known Activations