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

    Neuronpedia

    INDEX
    Explanations

    moves leading to a result

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    arse
    -0.08
     र
    -0.07
     krachtige
    -0.07
     कलाकार
    -0.07
     dealt
    -0.07
    ovanje
    -0.07
    슨
    -0.07
    tracted
    -0.07
    �
    -0.07
    aha
    -0.07
    POSITIVE LOGITS
     Unsafe
    0.08
     immediately
    0.08
     sarebbe
    0.08
     alleine
    0.08
     последствия
    0.08
     amanhã
    0.08
     Lonely
    0.08
     учреждения
    0.08
     worsening
    0.08
     legality
    0.07
    Act Density 0.017%

    No Known Activations