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

    Neuronpedia

    INDEX
    Explanations

    references to Java packages and classes

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

    After a period in a Java-like package name

    np_acts-logits-general · gemini-2.0-flash

    apache

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Попис
    -0.49
    Geografie
    -0.48
    ExecuteReader
    -0.47
    chapp
    -0.44
    TRAILING
    -0.42
    ższe
    -0.42
     toc
    -0.41
    submitted
    -0.41
    çim
    -0.40
     invita
    -0.40
    POSITIVE LOGITS
    apache
    0.69
    Datuak
    0.67
    Personendaten
    0.66
    AxisAlignment
    0.63
    Hdr
    0.61
     дописавши
    0.59
    zko
    0.59
    evos
    0.59
    springframework
    0.57
     يتيمه
    0.57
    Act Density 0.079%

    No Known Activations