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

    Neuronpedia

    INDEX
    Explanations

    lack of human experience

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     મદ
    0.42
    ど
    0.42
    list
    0.41
    UTICAL
    0.40
    緩
    0.40
     পিলার
    0.39
    調
    0.39
    нь
    0.38
    日常
    0.38
    γρά
    0.38
    POSITIVE LOGITS
     sentient
    0.81
     humanos
    0.75
     human
    0.71
    人类
    0.70
     humans
    0.69
     humanas
    0.68
     mensch
    0.68
     humanoid
    0.66
     انسان
    0.64
     humano
    0.64
    Act Density 0.394%

    No Known Activations