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

    Neuronpedia

    INDEX
    Explanations

    programming and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     for
    0.50
    ed
    0.43
    ↵
    0.43
    ز
    0.38
    ли
    0.38
     and
    0.37
    el
    0.36
    PARTY
    0.36
    う
    0.35
    ای
    0.35
    POSITIVE LOGITS
    ların
    0.34
    ^^
    0.32
     BVHTree
    0.31
    EEP
    0.30
     Rizal
    0.30
     i
    0.30
    tene
    0.30
    nake
    0.30
    tbLabel
    0.29
    0.29
    Act Density 0.000%

    No Known Activations