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

    Neuronpedia

    INDEX
    Explanations

    verb followed by recipients

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     إذا
    0.21
    apad
    0.21
     کیسے
    0.20
     ange
    0.20
     by
    0.20
     pursuant
    0.20
     schnell
    0.20
    baren
    0.20
    ్ఞ
    0.19
     وي
    0.19
    POSITIVE LOGITS
     them
    0.35
     उन्हें
    0.27
     it
    0.27
     туда
    0.26
     people
    0.24
     these
    0.23
    这
    0.22
     this
    0.22
     there
    0.22
     him
    0.21
    Act Density 0.444%

    No Known Activations