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

    Neuronpedia

    INDEX
    Explanations

    expressions describing comparisons or relative attributes

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

    relative characteristics and comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    enumii
    -0.54
     linkovi
    -0.52
     Italijani
    -0.47
    ENTION
    -0.44
    enumi
    -0.43
     pinulongan
    -0.43
     Савезне
    -0.43
    endom
    -0.42
    原始内容存档
    -0.42
    ulso
    -0.41
    POSITIVE LOGITS
     relative
    1.40
    relative
    1.11
     relatif
    1.09
     Relative
    1.09
     relativa
    1.02
    相對
    1.00
    Relative
    1.00
    相对
    0.99
     relativo
    0.94
     RELATIVE
    0.93
    Act Density 0.033%

    No Known Activations