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

    Neuronpedia

    INDEX
    Explanations

    questioning phrases and contextually related terms

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

    what's followed by

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     HasFactory
    -0.60
     defaultstate
    -0.52
    atguigu
    -0.50
     justru
    -0.49
    原始内容存档于
    -0.48
    eramente
    -0.47
     navideña
    -0.47
     sekunder
    -0.46
     cardíaca
    -0.46
     danach
    -0.46
    POSITIVE LOGITS
    Wanna
    0.49
    Gotta
    0.45
     Wanna
    0.44
    s
    0.41
    lec
    0.41
     Lime
    0.40
     lotta
    0.40
     gotta
    0.40
     tryna
    0.40
     Easy
    0.39
    Act Density 0.006%

    No Known Activations