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

    Neuronpedia

    INDEX
    Explanations

    should be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cuyas
    0.35
     losing
    0.35
     muốn
    0.35
     cuyos
    0.35
     whose
    0.34
     cuyo
    0.33
     ganhou
    0.33
     tahu
    0.33
     oferece
    0.33
     spends
    0.32
    POSITIVE LOGITS
     occur
    0.66
    occur
    0.57
     reflect
    0.56
     consisted
    0.56
     occurred
    0.55
     coincide
    0.54
     differ
    0.54
     vary
    0.53
     hinge
    0.53
     arise
    0.52
    Act Density 0.023%

    No Known Activations