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

    Neuronpedia

    INDEX
    Explanations

    inspires/intrigued

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     necesitamos
    -0.09
     اللازمة
    -0.09
     سيتم
    -0.09
     необходимые
    -0.09
     tarv
    -0.09
     bomo
    -0.08
     We'll
    -0.08
     necesidades
    -0.08
     जरूरत
    -0.08
     we'll
    -0.08
    POSITIVE LOGITS
     intrig
    0.25
     intrigued
    0.25
     fascin
    0.22
     inspires
    0.22
     intriguing
    0.20
     fascinated
    0.19
     resonates
    0.19
     faszin
    0.19
     chamou
    0.19
     struck
    0.18
    Act Density 0.087%

    No Known Activations