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

    Neuronpedia

    INDEX
    Explanations

    objects and containers in various contexts

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

    inside containers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.46
    хьтан
    -0.45
     otomatig
    -0.45
    Tembelea
    -0.43
    Географиясе
    -0.43
    angliski
    -0.43
    rungsseite
    -0.43
    CppCodeGen
    -0.42
     Signalez
    -0.42
    فایل‌لار
    -0.41
    POSITIVE LOGITS
     inside
    0.63
    inside
    0.59
     INSIDE
    0.56
    Inside
    0.52
     Inside
    0.52
    里面
    0.47
    里面的
    0.47
    PathParam
    0.47
     dedans
    0.46
    dentro
    0.45
    Act Density 0.099%

    No Known Activations