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

    Neuronpedia

    INDEX
    Explanations

    names in introductory phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    碉
    0.72
     thermonuclear
    0.68
     NTFS
    0.68
    aol
    0.67
    殄
    0.66
     NYSE
    0.65
     DoD
    0.64
     हिटलर
    0.63
     적용
    0.63
     NSFW
    0.62
    POSITIVE LOGITS
     El
    1.10
     Ch
    1.02
     Bella
    1.02
     Luna
    1.01
     Ak
    1.01
     Maria
    0.99
     Luz
    0.96
     Lila
    0.96
     bernama
    0.95
     Alex
    0.94
    Act Density 0.190%

    No Known Activations