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

    Neuronpedia

    INDEX
    Explanations

    survivors and characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     അവളുടെ
    0.83
    她的
    0.82
     hairstyles
    0.80
     her
    0.75
    给她
    0.75
     hairstyle
    0.75
    Ꮠ
    0.75
    蛲
    0.75
     neka
    0.74
    差距
    0.73
    POSITIVE LOGITS
     Sur
    1.22
     Survivors
    1.19
     Pre
    1.15
     survivors
    1.06
    Sur
    1.02
    Pre
    0.99
     pre
    0.99
    Surviv
    0.98
    Survived
    0.97
     Surv
    0.95
    Act Density 0.001%

    No Known Activations