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

    Neuronpedia

    INDEX
    Explanations

    ways to cope with stress

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pathologies
    0.63
     magnitudes
    0.56
     deformations
    0.56
     iteratively
    0.56
     violently
    0.55
     instantiated
    0.54
     instabilities
    0.52
     horribly
    0.52
     monotonically
    0.52
     horrible
    0.51
    POSITIVE LOGITS
     kiddos
    0.61
    Trusted
    0.49
     hefty
    0.49
    더라고
    0.48
     snag
    0.48
     culprits
    0.48
    妩
    0.47
     sidelined
    0.46
     culprit
    0.46
     isn
    0.46
    Act Density 0.003%

    No Known Activations