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

    Neuronpedia

    INDEX
    Explanations

    word beginnings followed by continuations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    addassa
    0.30
    avgsalary
    0.29
     المراجعه
    0.28
    gmzy
    0.27
    salaryfrom
    0.26
    पाउंड
    0.26
    िरिक्स
    0.25
    aeskeygenassist
    0.25
     Polaribacter
    0.24
    QTTR
    0.24
    POSITIVE LOGITS
    -
    0.35
    i
    0.34
    z
    0.34
    j
    0.32
    v
    0.32
    r
    0.32
    l
    0.31
    u
    0.30
    d
    0.29
    b
    0.29
    Act Density 0.440%

    No Known Activations