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

    Neuronpedia

    INDEX
    Explanations

    transitive property, if-then statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     polymorphism
    0.50
     ricotta
    0.50
     prerog
    0.47
     progen
    0.47
     kanilang
    0.46
     slavery
    0.46
     terroir
    0.46
     cardamom
    0.46
     birdseye
    0.46
     chorizo
    0.45
    POSITIVE LOGITS
     υπό
    0.47
    omb
    0.46
    wf
    0.45
    ür
    0.45
    lor
    0.45
     விழு
    0.45
    blocks
    0.44
    lis
    0.44
    Arts
    0.43
    body
    0.43
    Act Density 0.005%

    No Known Activations