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

    Neuronpedia

    INDEX
    Explanations

    Translate text instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    二百
    0.28
    ⸩
    0.28
     kullanım
    0.27
     восем
    0.27
    𒂵
    0.27
    pflege
    0.26
    ༨
    0.26
     umfasst
    0.26
     sonuç
    0.26
     Олександр
    0.25
    POSITIVE LOGITS
    ↵
    0.32
     “
    0.26
     Only
    0.26
     The
    0.25
     -
    0.25
    ay
    0.25
    ing
    0.24
     Cl
    0.24
      
    0.24
     Fac
    0.24
    Act Density 0.000%

    No Known Activations