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

    Neuronpedia

    INDEX
    Explanations

    specific nouns and their descriptors related to various objects or items

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

    noun followed by a common modifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     område
    -0.39
    You
    -0.39
     superiori
    -0.38
     lecz
    -0.36
    The
    -0.36
     forklar
    -0.35
     dlatego
    -0.35
     forstå
    -0.34
     Erklärung
    -0.34
     steder
    -0.34
    POSITIVE LOGITS
    脚注の使い方
    0.76
    iſche
    0.75
    expandindo
    0.74
    ſſung
    0.74
    enablog
    0.74
     autorytatywna
    0.74
    <unused79>
    0.73
    majánló
    0.73
    <unused47>
    0.73
    <unused41>
    0.73
    Act Density 0.099%

    No Known Activations