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

    Neuronpedia

    INDEX
    Explanations

    requests to write about love

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     intellig
    0.86
    لها
    0.86
    \
    0.80
    land
    0.79
     cameras
    0.78
    lar
    0.77
     immers
    0.77
    لع
    0.77
    لية
    0.75
    los
    0.74
    POSITIVE LOGITS
    IN
    1.04
     was
    0.93
    ン
    0.92
    AZ
    0.91
     Varan
    0.88
    certificate
    0.87
    ED
    0.84
    a
    0.84
    ET
    0.82
    salaryfrom
    0.82
    Act Density 0.009%

    No Known Activations