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

    Neuronpedia

    INDEX
    Explanations

    stakeholders

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     СРСР
    -0.07
     funeral
    -0.07
    ropical
    -0.06
     remix
    -0.06
    ském
    -0.06
    وير
    -0.06
    ивания
    -0.06
    azı
    -0.06
    Compact
    -0.06
     perimeter
    -0.06
    POSITIVE LOGITS
     stakeholders
    0.10
     FloatingActionButton
    0.07
    �
    0.07
     bere
    0.06
    oracle
    0.06
    CLAIM
    0.06
    民
    0.06
     Tou
    0.06
    จน
    0.06
     Mak
    0.06
    Act Density 0.004%

    No Known Activations