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

    Neuronpedia

    INDEX
    Explanations

    introducing reasons or options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    پ
    0.49
     homers
    0.47
    !”,
    0.46
    berto
    0.45
    $，
    0.45
    ले
    0.43
    ین
    0.42
     인한
    0.42
     justement
    0.42
    दीश
    0.41
    POSITIVE LOGITS
    ↵↵
    0.89
    ↵
    0.83
              
    0.71
          
    0.69
    </h2>
    0.68
    ↵↵↵
    0.64
    ↵↵↵↵↵
    0.63
    ↵↵↵↵
    0.62
                    
    0.62
               
    0.62
    Act Density 0.444%

    No Known Activations