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

    Neuronpedia

    INDEX
    Explanations

    higher or unlock

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ilever
    0.42
    મુ
    0.39
     मेयर
    0.38
    宣言
    0.38
     PROCUREMENT
    0.38
     år
    0.38
    ទេ
    0.38
    aiman
    0.38
    ర్లు
    0.37
     ಮೀ
    0.37
    POSITIVE LOGITS
     ls
    0.42
     hillside
    0.41
    LS
    0.40
    الہ
    0.40
     Als
    0.39
    E
    0.38
     Darwin
    0.37
     Cs
    0.37
     Schloss
    0.37
     PS
    0.37
    Act Density 0.000%

    No Known Activations