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

    Neuronpedia

    INDEX
    Explanations

    expressions of quantity or degree

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

    quantity and comparison

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.51
    SequentialGroup
    -0.47
     censiti
    -0.41
     defaultstate
    -0.41
    __::
    -0.37
    tinyos
    -0.35
     Wide
    -0.33
     mang
    -0.32
    esta
    -0.32
     CreateTagHelper
    -0.32
    POSITIVE LOGITS
    раздо
    0.84
     jauh
    0.68
     гораздо
    0.60
     worse
    0.59
     sharper
    0.58
    évaluateur
    0.57
    worse
    0.57
     намного
    0.57
     much
    0.56
    훨
    0.56
    Act Density 0.163%

    No Known Activations