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

    Neuronpedia

    INDEX
    Explanations

    ++

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    original
    -0.07
     describing
    -0.07
     alın
    -0.06
    sessionId
    -0.06
    Denied
    -0.06
    선을
    -0.06
     AuthenticationService
    -0.06
    118
    -0.06
    ोषण
    -0.06
    liğini
    -0.06
    POSITIVE LOGITS
    ++
    0.11
    ++,
    0.08
    Depart
    0.07
    ++.
    0.07
    Ep
    0.07
    antly
    0.07
     escapes
    0.07
    Pawn
    0.06
     focusing
    0.06
     honey
    0.06
    Act Density 0.005%

    No Known Activations