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

    Neuronpedia

    INDEX
    Explanations

    the presence of specific pronouns and reference phrases indicating personal or customer-focused terms

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

    go to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tagext
    -0.44
    setViewportView
    -0.44
     Überblick
    -0.40
     kelahiran
    -0.40
     jelasnya
    -0.40
     betrekking
    -0.39
     bijzonder
    -0.39
     certeza
    -0.39
     içeri
    -0.39
     getSize
    -0.38
    POSITIVE LOGITS
     goto
    0.48
     wireType
    0.46
    Viitteet
    0.46
     destination
    0.45
     Went
    0.45
     attend
    0.44
    Went
    0.43
     autorytatywna
    0.43
     goTo
    0.43
     destinations
    0.42
    Act Density 0.039%

    No Known Activations