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

    Neuronpedia

    INDEX
    Explanations

    adding controls to interface

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Model
    0.53
     APPLICATION
    0.53
     appliqué
    0.52
     rápido
    0.52
     aplicada
    0.52
     Sora
    0.50
     Model
    0.49
    顼
    0.48
    ך
    0.47
    AD
    0.46
    POSITIVE LOGITS
    ت
    0.65
     husbands
    0.53
    ighet
    0.52
    <0x9C>
    0.50
    oon
    0.49
    ப்பா
    0.48
    rong
    0.48
     ferns
    0.48
     creditors
    0.47
    ත්
    0.47
    Act Density 0.000%

    No Known Activations