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

    Neuronpedia

    INDEX
    Explanations

    code and programming keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     RTX
    0.43
     Hobbit
    0.38
     ды
    0.37
     Sorrow
    0.37
     Detection
    0.37
    nonce
    0.37
     Fever
    0.36
     çap
    0.36
     Radical
    0.36
    いただきました
    0.36
    POSITIVE LOGITS
     entra
    0.43
    anis
    0.43
    ageo
    0.40
    INIS
    0.37
    amand
    0.37
     manageable
    0.36
    有望
    0.36
    )}}{\
    0.35
    తుందని
    0.35
    WriteLine
    0.35
    Act Density 0.000%

    No Known Activations