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

    Neuronpedia

    INDEX
    Explanations

    lesson plans

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     chemins
    0.41
     El
    0.40
     മറ്റു
    0.40
     phenols
    0.40
     heb
    0.39
     മറ്റ്
    0.39
     poseen
    0.39
     strategies
    0.39
     tall
    0.39
     common
    0.39
    POSITIVE LOGITS
    Develop
    0.43
     costado
    0.42
    iophene
    0.41
    otip
    0.41
     đỡ
    0.41
    Aggregate
    0.40
     осмо
    0.40
    amalla
    0.40
    nesset
    0.39
    荠
    0.39
    Act Density 0.001%

    No Known Activations