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

    Neuronpedia

    INDEX
    Explanations

    references to improvement and positive change

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

    comparing options or quality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     umana
    -0.48
    Vidite
    -0.47
     riuscito
    -0.46
     ProtoMessage
    -0.45
    ViewFeatures
    -0.45
    principalColumn
    -0.44
    disposing
    -0.44
     [*]
    -0.44
     boyunca
    -0.42
     PyLong
    -0.42
    POSITIVE LOGITS
    waitKey
    0.43
     alternatives
    0.42
     choice
    0.40
     organic
    0.40
     snippetHide
    0.38
     Organic
    0.37
    有机
    0.37
     đẳng
    0.36
     choices
    0.36
     autorytatywna
    0.36
    Act Density 0.170%

    No Known Activations