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

    Neuronpedia

    INDEX
    Explanations

    case assessment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     سن
    0.38
     genocide
    0.38
     ዓይነት
    0.37
    িনিয়ার
    0.37
    }}^{(
    0.37
    лкой
    0.37
     yet
    0.36
     Yet
    0.35
     desses
    0.35
    checked
    0.35
    POSITIVE LOGITS
    pR
    0.44
    \[
    0.43
     deaminase
    0.43
     sleeper
    0.42
     Assessments
    0.41
     Assessment
    0.40
    nG
    0.39
     assess
    0.39
    bP
    0.38
     LH
    0.38
    Act Density 0.000%

    No Known Activations