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

    Neuronpedia

    INDEX
    Explanations

    common short words and pronouns, especially "we", "are", "is", and "our".

    oai_token-act-pair · gemini-2.0-flash

    words indicating presence or location

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    Hammer
    -0.46
    solids
    -0.45
    ValueGeneration
    -0.44
     Hammer
    -0.43
    writeObject
    -0.43
     pou
    -0.41
    PullParser
    -0.40
    tencent
    -0.40
    نسية
    -0.40
    (−
    -0.40
    POSITIVE LOGITS
     AssemblyCulture
    0.86
    here
    0.73
    <?
    0.71
     here
    0.69
     Ici
    0.65
    脚注の使い方
    0.65
     GenerationType
    0.61
     aquí
    0.60
    HERE
    0.59
     tää
    0.59
    Act Density 0.506%

    No Known Activations