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

    Neuronpedia

    INDEX
    Explanations

    tilde symbol

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    به
    2.69
    ഈ
    2.64
    ক
    2.53
    um
    2.48
    Př
    2.36
    gings
    2.33
     luego
    2.32
     cuales
    2.31
    ย
    2.30
    க
    2.26
    POSITIVE LOGITS
    ,~
    3.98
    ~\
    3.45
    𝘶
    3.31
    ~~~~~~~~~~~~~~~~
    3.28
    isempty
    3.27
    .~
    3.15
    :~
    3.02
    }~
    2.98
    
    2.94
    ~(
    2.92
    Act Density 0.038%

    No Known Activations