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

    Neuronpedia

    INDEX
    Explanations

    random strings of characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ״
    0.26
    ૢ
    0.25
    觡
    0.25
    ולוג
    0.25
    ׳
    0.25
    ровка
    0.24
    ⟋
    0.24
    ологи
    0.24
     budgeting
    0.24
    ხვევ
    0.24
    POSITIVE LOGITS
     S
    0.28
    END
    0.27
    ffffff
    0.25
     C
    0.25
    5
    0.25
    any
    0.24
    6
    0.24
     N
    0.24
     novembre
    0.24
    N
    0.23
    Act Density 0.086%

    No Known Activations