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

    Neuronpedia

    INDEX
    Explanations

    documents and tutorials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     threat
    0.54
    threat
    0.50
    ター
    0.48
    0.48
    ème
    0.47
     threatened
    0.47
     Threat
    0.47
     Rees
    0.47
    2
    0.46
    Tube
    0.46
    POSITIVE LOGITS
     येईल
    0.48
     epidemics
    0.47
    了很多
    0.47
     installers
    0.46
     arī
    0.46
     informacije
    0.46
    нит
    0.44
     cũng
    0.43
     allergens
    0.43
     egyéb
    0.43
    Act Density 0.000%

    No Known Activations