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

    Neuronpedia

    INDEX
    Explanations

    Error logs with timestamps

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ；↵
    -0.07
    incinn
    -0.06
     Schwarz
    -0.06
     امتی
    -0.06
     Department
    -0.06
    _ser
    -0.06
    ourke
    -0.06
    Joy
    -0.06
    uers
    -0.06
    .View
    -0.06
    POSITIVE LOGITS
     replaced
    0.07
     WV
    0.06
     ev
    0.06
    анов
    0.06
     fined
    0.06
    нова
    0.06
     gradient
    0.06
    řich
    0.06
     sélection
    0.06
     victims
    0.06
    Act Density 0.015%

    No Known Activations