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

    Neuronpedia

    INDEX
    Explanations

    management and adjustment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     folate
    0.99
     fuselage
    0.99
     currents
    0.96
     hangover
    0.96
     cashmere
    0.95
     ALA
    0.94
     gorge
    0.93
     kayaking
    0.93
     flamingo
    0.93
     transgene
    0.92
    POSITIVE LOGITS
    А
    1.00
    Т
    0.98
    О
    0.95
    си
    0.94
    ди
    0.93
    You
    0.91
    a
    0.90
    <b>
    0.84
    Это
    0.81
    дно
    0.79
    Act Density 0.003%

    No Known Activations