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

    Neuronpedia

    INDEX
    Explanations

    words and phrases that indicate acknowledgment or affirmation

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

    but also

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    舺
    -0.57
    httphttps
    -0.55
    GetEnumerator
    -0.47
    AndEndTag
    -0.46
    windowFixed
    -0.44
     hochzeit
    -0.43
    uruhan
    -0.42
    szönöm
    -0.41
     nhiên
    -0.40
    ография
    -0.40
    POSITIVE LOGITS
     esternos
    0.47
     PeEnEo
    0.47
    但也
    0.44
    forbes
    0.42
     CreateTagHelper
    0.41
     Italijanski
    0.39
     deep
    0.38
    たちも
    0.38
     also
    0.37
     EdgeInsets
    0.37
    Act Density 0.021%

    No Known Activations