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

    Neuronpedia

    INDEX
    Explanations

    through more

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    剜
    0.42
    Ե
    0.39
    0.38
    íncipe
    0.38
    ğlu
    0.38
    秣
    0.37
    㤈
    0.37
    ქვთ
    0.36
     snapshots
    0.36
    élevage
    0.36
    POSITIVE LOGITS
     Show
    0.44
     Zum
    0.40
     Apr
    0.38
     show
    0.38
     திருதியை
    0.37
     gravity
    0.36
     zob
    0.36
     ديسمبر
    0.36
    Show
    0.35
    Zum
    0.35
    Act Density 0.000%

    No Known Activations