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

    Neuronpedia

    INDEX
    Explanations

    not negate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Orc
    0.51
     tadi
    0.49
     vendeurs
    0.49
     memperbaiki
    0.48
     océano
    0.47
     hidup
    0.47
     daerah
    0.46
     ਸਾ
    0.46
     알고
    0.45
    Roy
    0.45
    POSITIVE LOGITS
    4
    0.45
     gelten
    0.44
    times
    0.43
    isses
    0.43
    xspace
    0.43
     kisses
    0.43
     explanations
    0.42
     impractical
    0.42
     Affairs
    0.41
     commissioned
    0.41
    Act Density 0.000%

    No Known Activations