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

    Neuronpedia

    INDEX
    Explanations

    certificates and evaluation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     clearly
    0.44
    keh
    0.43
     plainly
    0.41
    ierung
    0.41
     menstru
    0.41
    ゙
    0.40
     cru
    0.39
     bew
    0.38
     →
    0.38
    iranja
    0.38
    POSITIVE LOGITS
    certificates
    0.51
     certific
    0.48
    cert
    0.48
    certificate
    0.48
    Evalu
    0.48
    Certificate
    0.46
     evaluator
    0.46
     certificate
    0.46
    Cert
    0.46
    Digital
    0.45
    Act Density 0.001%

    No Known Activations