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

    Neuronpedia

    INDEX
    Explanations

    trapped, builds, instructions, iOS

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    أة
    0.42
     alteration
    0.39
     Readings
    0.39
    paragus
    0.38
    etrain
    0.38
    銖
    0.38
    हारा
    0.38
     Arial
    0.37
    疳
    0.37
    朓
    0.37
    POSITIVE LOGITS
    ссий
    0.39
     explore
    0.38
     exploring
    0.38
    浜
    0.37
     dive
    0.37
     explorar
    0.35
    oming
    0.34
    শিল্প
    0.34
     gull
    0.34
     核
    0.34
    Act Density 0.000%

    No Known Activations