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

    Neuronpedia

    INDEX
    Explanations

    invitations, jobs, scanning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    yld
    0.50
     ಹೊಂದ
    0.49
     Algon
    0.46
    ͹
    0.45
     Cependant
    0.45
    ouz
    0.45
    다면
    0.45
    𝑂
    0.45
    IDE
    0.44
    ivert
    0.44
    POSITIVE LOGITS
                
    0.61
                    
    0.57
     opinions
    0.51
                        
    0.46
    :
    0.46
    ]
    0.46
     från
    0.46
    [
    0.46
    \
    0.44
    ‌
    0.44
    Act Density 0.000%

    No Known Activations