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

    Neuronpedia

    INDEX
    Explanations

    pieces

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     charité
    -0.69
     ergo
    -0.68
     Ergo
    -0.65
     excès
    -0.63
     rembour
    -0.61
     spare
    -0.60
     Spare
    -0.60
     pédagogique
    -0.60
     líqu
    -0.59
     Púb
    -0.59
    POSITIVE LOGITS
    ://"
    0.60
    Искәрмәләр
    0.59
    AJAS
    0.56
    ++
    0.56
    Confira
    0.54
    BeginInit
    0.53
    '):
    0.53
    []
    0.52
     }</
    0.52
    "):
    0.50
    Act Density 0.172%

    No Known Activations