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

    Neuronpedia

    INDEX
    Explanations

    actions meant to achieve a goal

    oai_token-act-pair · gemini-2.0-flash

    words related to actions or purposes

    np_token-act-pair-logits · gpt-4o-mini

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    kuuta
    -0.64
    Portály
    -0.59
    Heraus
    -0.48
    crollView
    -0.48
    "]}
    -0.48
     trouvait
    -0.47
     Dete
    -0.46
     aient
    -0.45
    ыгана
    -0.45
    HandlerContext
    -0.45
    POSITIVE LOGITS
     raise
    0.68
    出版年
    0.66
     highlight
    0.60
    FailureListener
    0.59
     convey
    0.59
     Administrativna
    0.55
    <?
    0.54
    قایناق‌لار
    0.51
    WriteTagHelper
    0.51
     showcase
    0.51
    Act Density 1.178%

    No Known Activations