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

    Neuronpedia

    INDEX
    Explanations

    numbers and prices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Recipe
    0.95
     धरोहर
    0.92
     Jour
    0.91
    Resize
    0.91
    tion
    0.89
    fjord
    0.88
     ఇటీ
    0.85
    Semi
    0.85
     Sources
    0.85
    ted
    0.84
    POSITIVE LOGITS
    }=\
    1.17
     terror
    1.13
     doubles
    1.09
     idea
    1.09
     azar
    1.09
     fellow
    1.05
     abad
    1.04
     retaliation
    1.04
     peintre
    1.04
     homosexual
    1.03
    Act Density 0.000%

    No Known Activations