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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating positive attributes or qualities in various contexts

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

    user input

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.46
    tagext
    -0.44
     IFTT
    -0.44
     otomatig
    -0.42
    цездатний
    -0.41
    aporan
    -0.41
    CastException
    -0.38
     Administrativna
    -0.37
    Style
    -0.36
    ͧ
    -0.36
    POSITIVE LOGITS
     CURIAM
    0.64
    WebVitals
    0.53
     MainAxisSize
    0.52
     zijne
    0.49
    genodigd
    0.48
    RectangleBorder
    0.44
    AccessorTable
    0.43
    InputBorder
    0.43
     iprot
    0.42
     wireType
    0.42
    Act Density 0.000%

    No Known Activations