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

    Neuronpedia

    INDEX
    Explanations

    pip install and build commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ன்
    0.52
    диви
    0.52
    தல
    0.50
    য়াল
    0.49
    л
    0.47
    जेंसी
    0.47
    з
    0.46
     fác
    0.46
     χρή
    0.46
    חת
    0.45
    POSITIVE LOGITS
    다
    0.70
     a
    0.48
    ’
    0.47
    lardan
    0.46
    1
    0.44
    ഡ്
    0.44
    の日
    0.44
    いますが
    0.44
    kee
    0.44
     infestation
    0.43
    Act Density 0.177%

    No Known Activations