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

    Neuronpedia

    INDEX
    Explanations

    if...then logic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     peroneal
    1.05
     mitigated
    1.02
    ственный
    1.02
    বন্ত
    0.97
     sidelined
    0.96
     bolstered
    0.96
     samh
    0.96
     externalities
    0.95
    重要的
    0.95
     bolster
    0.94
    POSITIVE LOGITS
    }$;
    0.98
    IN
    0.90
    }$
    0.86
    }$.
    0.82
     Pray
    0.80
      
    0.80
    Pray
    0.78
    X
    0.77
    та
    0.76
    you
    0.76
    Act Density 0.006%

    No Known Activations