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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to software testing processes

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

    does only

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     defaultstate
    -0.67
    CppCodeGen
    -0.59
     '{@
    -0.54
    ſſung
    -0.53
    ſchen
    -0.53
     Verſ
    -0.53
    LabelTagHelper
    -0.52
    ſelves
    -0.52
     silêncio
    -0.52
    crumbs
    -0.51
    POSITIVE LOGITS
    <eos>
    0.38
     usually
    0.34
     generally
    0.33
    ]-->
    0.33
     appelez
    0.31
    TargetException
    0.30
    sweise
    0.29
     widely
    0.28
     utr
    0.27
     always
    0.27
    Act Density 0.165%

    No Known Activations