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

    Neuronpedia

    INDEX
    Explanations

    references to broken or shattered objects, particularly glass

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

    shattered glass into fragments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ब्रेकडाउन
    -0.65
    oneofs
    -0.44
    GHIJKLM
    -0.40
     Autorizaciones
    -0.39
    Enllaces
    -0.36
    errHandler
    -0.36
     odp
    -0.36
     Peat
    -0.36
     saites
    -0.36
     التن
    -0.35
    POSITIVE LOGITS
     glass
    1.55
     Glass
    1.37
    glass
    1.32
    Glass
    1.32
     GLASS
    1.26
    GLASS
    1.16
    玻璃
    1.13
     glassware
    1.04
    ガラス
    1.02
     vidrio
    0.99
    Act Density 0.028%

    No Known Activations