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

    Neuronpedia

    INDEX
    Explanations

    interest/desire

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fod
    0.41
     hated
    0.40
     সহ্য
    0.37
     deserve
    0.36
     susah
    0.36
     boring
    0.35
     iframe
    0.35
     invertebr
    0.35
     runt
    0.35
     suffer
    0.35
    POSITIVE LOGITS
     eager
    0.96
     intrigued
    0.86
     keen
    0.79
     fascinated
    0.79
     interested
    0.77
     excited
    0.77
     motivated
    0.74
     desirous
    0.74
     concerned
    0.73
     compelled
    0.72
    Act Density 0.295%

    No Known Activations