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

    Neuronpedia

    INDEX
    Explanations

    do something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    p
    1.20
    als
    1.16
    ut
    1.14
    ↵
    1.13
     comunidades
    1.13
    昷
    1.13
    pou
    1.11
    Edition
    1.11
     doves
    1.09
     communs
    1.09
    POSITIVE LOGITS
    ל
    1.79
    er
    1.46
    рная
    1.32
     needful
    1.31
    ről
    1.30
    риев
    1.26
    시에
    1.24
    ли
    1.23
    জনকে
    1.22
    ম
    1.16
    Act Density 0.171%

    No Known Activations