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

    Neuronpedia

    INDEX
    Explanations

    location prepositions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    round
    0.45
    sho
    0.39
    amor
    0.36
     poin
    0.36
    人
    0.36
    வைத்து
    0.35
    sub
    0.34
    pagination
    0.34
    scar
    0.34
    खी
    0.34
    POSITIVE LOGITS
    を防
    0.44
    昛
    0.43
    を起こ
    0.42
    onesian
    0.41
     സ്വ
    0.41
     निजी
    0.40
     Localization
    0.40
    Ŭ
    0.40
     निर्देशों
    0.39
     됩니다
    0.39
    Act Density 0.001%

    No Known Activations