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

    Neuronpedia

    INDEX
    Explanations

    health insurance and consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mesta
    0.95
     lern
    0.87
     murder
    0.84
    ৃহ
    0.80
    orestation
    0.80
    murder
    0.78
     Topology
    0.77
    ேத்க
    0.77
    phrine
    0.77
     lhe
    0.76
    POSITIVE LOGITS
    iness
    1.52
    ier
    1.27
    ily
    1.24
     care
    1.22
    iest
    1.20
    状况
    1.13
    span
    1.09
    CARE
    1.09
    ಕರ
    1.08
     insurance
    1.08
    Act Density 0.075%

    No Known Activations