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

    Neuronpedia

    INDEX
    Explanations

    past participle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     평
    1.21
     알
    1.18
    ślin
    1.17
    یثیت
    1.16
    ධා
    1.15
    ന്യാ
    1.13
    ത്വം
    1.11
     flotation
    1.10
    있는
    1.10
     funciona
    1.10
    POSITIVE LOGITS
    est
    1.31
    reicher
    1.27
    援助
    1.19
     importantly
    1.16
     meagre
    1.13
    s
    1.07
    するなど
    1.07
    re
    1.07
    nya
    1.06
    rant
    1.05
    Act Density 0.000%

    No Known Activations