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

    Neuronpedia

    INDEX
    Explanations

    diversity, inclusion, equality, National, SA

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     veloc
    0.78
     prefixed
    0.78
     shortstop
    0.77
     하늘
    0.74
     couches
    0.70
     captcha
    0.70
     ABSORBED
    0.70
     tRNA
    0.69
     डाइजेस्टिव
    0.69
    Scalars
    0.69
    POSITIVE LOGITS
     equal
    1.60
     Equal
    1.54
     diversity
    1.47
    Equal
    1.46
     Diversity
    1.43
    equal
    1.42
    Diversity
    1.38
     equality
    1.36
     igualdad
    1.31
    diversity
    1.27
    Act Density 0.046%

    No Known Activations