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

    Neuronpedia

    INDEX
    Explanations

    needs information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    न
    0.90
    Technology
    0.88
    ר
    0.83
     perché
    0.81
    াতি
    0.78
     scelta
    0.78
    Financial
    0.77
    仑
    0.75
    ر
    0.75
     vantaggio
    0.74
    POSITIVE LOGITS
     omnichannel
    0.82
     embark
    0.78
     PoE
    0.75
     PFAS
    0.75
     offenbar
    0.74
     tato
    0.73
     engross
    0.73
     tou
    0.72
     starring
    0.72
     lockout
    0.72
    Act Density 0.002%

    No Known Activations