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

    Neuronpedia

    INDEX
    Explanations

    code preparation and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    clothing
    0.75
    night
    0.72
    layers
    0.72
     representando
    0.71
    dress
    0.70
    photo
    0.69
    organizations
    0.68
    massive
    0.68
    david
    0.68
    挑选
    0.68
    POSITIVE LOGITS
     ilgili
    0.81
    ్
    0.77
    ítmény
    0.76
     thì
    0.76
     réfé
    0.75
     méth
    0.73
     Köz
    0.73
     tím
    0.71
     não
    0.71
    oodoo
    0.70
    Act Density 0.004%

    No Known Activations