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

    Neuronpedia

    INDEX
    Explanations

    story about

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     developed
    0.93
     depict
    0.87
     develop
    0.84
    developed
    0.84
     depicts
    0.84
     constructed
    0.83
     deal
    0.80
     deals
    0.79
     designed
    0.77
    Developed
    0.77
    POSITIVE LOGITS
    Set
    0.77
     Set
    0.76
     Coefficient
    0.76
     coefficients
    0.75
    Coefficient
    0.73
     allergens
    0.71
     Theoretically
    0.68
    मूलन
    0.68
     coefficient
    0.68
    coefficient
    0.68
    Act Density 0.015%

    No Known Activations