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

    Neuronpedia

    INDEX
    Explanations

    food safety and measurement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hearth
    0.39
     defaul
    0.39
    鉆
    0.39
    elim
    0.37
    墂
    0.37
     คูณ
    0.37
    циа
    0.36
     وسائل
    0.36
     Nilsson
    0.36
     socially
    0.36
    POSITIVE LOGITS
    Severity
    0.39
    这
    0.39
     CTR
    0.38
    obedience
    0.38
    iterator
    0.37
     syg
    0.36
    Measure
    0.35
    obe
    0.35
    ancis
    0.35
    鼹
    0.35
    Act Density 0.000%

    No Known Activations