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

    Neuronpedia

    INDEX
    Explanations

    appearance descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ০০
    1.45
        
    1.34
     మంది
    1.22
    0
    1.18
    };
    1.16
          
    1.16
    𝙱
    1.15
                
    1.13
                   
    1.13
    מ
    1.13
    POSITIVE LOGITS
    ist
    1.56
    ა
    1.55
    ین
    1.52
     dennoch
    1.41
    ية
    1.40
    ית
    1.32
     loob
    1.28
    ți
    1.23
     consigui
    1.23
    യാണ്
    1.22
    Act Density 0.008%

    No Known Activations