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

    Neuronpedia

    INDEX
    Explanations

    specific nouns and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.57
    Have
    0.52
    Are
    0.51
    G
    0.50
    (
    0.50
    Let
    0.50
    Michigan
    0.48
    V
    0.47
    LAH
    0.47
    Most
    0.47
    POSITIVE LOGITS
     বিটিআই
    0.55
     traumatic
    0.50
     रखकर
    0.50
    ômios
    0.48
    testAvg
    0.48
     contempl
    0.48
     clamping
    0.48
    𝚇
    0.47
     contemplation
    0.47
     contemplated
    0.47
    Act Density 0.000%

    No Known Activations