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

    Neuronpedia

    INDEX
    Explanations

    saving souls and people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Parent
    0.97
    مد
    0.89
    rologist
    0.87
    ändige
    0.83
    plications
    0.83
    PARENT
    0.83
    Factors
    0.82
     berücksichtigt
    0.82
     సినిమాలో
    0.82
     persönlichen
    0.82
    POSITIVE LOGITS
     prisoners
    1.68
     sinners
    1.62
     souls
    1.61
     criminals
    1.58
     travelers
    1.56
     captives
    1.52
     strangers
    1.49
     mortals
    1.49
     passers
    1.48
     unsuspecting
    1.47
    Act Density 0.081%

    No Known Activations