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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal feelings and reflections

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

    Follows "sure," a name, "way," or "ascii"

    np_acts-logits-general · gemini-2.0-flash

    specific sequences like "way analysis"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :+:
    -0.53
    ViewFeatures
    -0.51
    новниш
    -0.48
    
    -0.46
    حياتها
    -0.46
     insuffisamment
    -0.45
    JvmStatic
    -0.45
     wynosi
    -0.45
     reck
    -0.44
    ensed
    -0.44
    POSITIVE LOGITS
    ztály
    0.62
     yun
    0.60
    crites
    0.59
     CreateTagHelper
    0.58
     ako
    0.56
     sobra
    0.56
     Sana
    0.55
     تانيه
    0.55
     wag
    0.55
     Hindi
    0.54
    Act Density 0.065%

    No Known Activations