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

    Neuronpedia

    INDEX
    Explanations

    asking about what

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ၀၀
    0.27
     uitvo
    0.25
    нга
    0.25
     umož
    0.25
    usercontent
    0.25
    .。
    0.25
     Frum
    0.25
     способны
    0.25
     Gottes
    0.24
    unication
    0.24
    POSITIVE LOGITS
     is
    0.37
    ，
    0.32
    は
    0.31
     was
    0.30
    、
    0.30
    ،
    0.29
     and
    0.29
    はもちろん
    0.28
    די
    0.27
    ט
    0.27
    Act Density 0.148%

    No Known Activations