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

    Neuronpedia

    INDEX
    Explanations

    pericyclic reactions, stereochemistry

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pyruvate
    0.62
    α
    0.54
     α
    0.53
     अल्फा
    0.51
     keto
    0.46
    alpha
    0.45
    園
    0.44
    Alpha
    0.44
     alpha
    0.44
    alph
    0.44
    POSITIVE LOGITS
     $[
    0.39
     зді
    0.38
    Ally
    0.38
     concerted
    0.38
    翼
    0.37
     YAML
    0.37
     negoti
    0.36
    gamer
    0.36
     능력
    0.35
    倝
    0.35
    Act Density 0.001%

    No Known Activations