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

    Neuronpedia

    INDEX
    Explanations

    signatures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    quets
    -0.06
     nouveau
    -0.06
    cuda
    -0.06
    /Q
    -0.06
     anomaly
    -0.06
     OBS
    -0.06
     tunes
    -0.06
     reproduced
    -0.06
    ’ll
    -0.06
    obe
    -0.06
    POSITIVE LOGITS
    .spark
    0.07
    figur
    0.07
    _codigo
    0.07
    CRYPT
    0.06
    pedia
    0.06
    679
    0.06
    ريق
    0.06
     tempor
    0.06
     BACK
    0.06
     الحر
    0.06
    Act Density 0.003%

    No Known Activations