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

    Neuronpedia

    INDEX
    Explanations

    code syntax fragments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Acetic
    0.31
    AGUE
    0.29
    Wallace
    0.29
    ABAB
    0.29
     perfused
    0.29
    Woods
    0.29
    Roasted
    0.28
    Église
    0.28
    鹹
    0.28
    AGT
    0.28
    POSITIVE LOGITS
     remembers
    0.32
     retr
    0.31
     thanked
    0.31
    return
    0.29
     Nazi
    0.29
     फिलहाल
    0.29
     elapsed
    0.29
     lackluster
    0.29
     trenut
    0.28
     admire
    0.28
    Act Density 0.346%

    No Known Activations