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

    Neuronpedia

    INDEX
    Explanations

    other languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    _
    0.38
      
    0.36
    ،
    0.34
    ",
    0.33
        
    0.33
            
    0.33
     (
    0.33
    0.33
     of
    0.32
    *
    0.32
    POSITIVE LOGITS
     drugih
    0.39
     ఇతర
    0.39
    <unused282>
    0.37
     diğer
    0.37
    その他
    0.36
     egyéb
    0.36
    <unused1861>
    0.36
    その他の
    0.36
    อื่นๆ
    0.35
    <unused553>
    0.34
    Act Density 0.166%

    No Known Activations