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

    Neuronpedia

    INDEX
    Explanations

    compens

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Compens
    -1.48
    compens
    -1.41
     compens
    -1.39
     compensate
    -1.38
     compensating
    -1.38
     compensated
    -1.29
     compensation
    -1.28
     compensatory
    -1.22
     Compensation
    -1.15
    compensation
    -1.09
    POSITIVE LOGITS
     larmes
    0.59
     varandra
    0.57
    الإنجليزية
    0.56
     démocr
    0.56
     ſche
    0.54
     utveckling
    0.53
     تانيه
    0.53
     quæ
    0.53
     météo
    0.52
     barnen
    0.52
    Act Density 0.007%

    No Known Activations