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

    Neuronpedia

    INDEX
    Explanations

    poems about topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ”,
    0.44
     ",
    0.41
    这意味着
    0.38
     refusal
    0.37
     само
    0.37
     ?,
    0.37
     ?",
    0.36
    лд
    0.36
    ਾਲ
    0.35
    UR
    0.35
    POSITIVE LOGITS
    ographie
    0.38
     trúc
    0.37
     Celebration
    0.36
    డిన
    0.36
     przy
    0.35
     Ordinance
    0.35
     Chandler
    0.35
     profunda
    0.35
     Come
    0.34
     شدت
    0.34
    Act Density 0.000%

    No Known Activations