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

    Neuronpedia

    INDEX
    Explanations

    Public awareness security

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     initiatives
    0.85
     efforts
    0.78
     Initiatives
    0.76
     تلاش
    0.74
     প্রচে
    0.71
    努力
    0.71
     effort
    0.70
     Efforts
    0.69
     esfuerzos
    0.69
     esforços
    0.67
    POSITIVE LOGITS
     sens
    0.77
     Sens
    0.74
    sens
    0.73
     orientación
    0.67
    orientation
    0.66
    Sens
    0.66
     camps
    0.64
    Orientation
    0.63
     Orientation
    0.62
     সৃষ্টির
    0.61
    Act Density 0.006%

    No Known Activations