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

    Neuronpedia

    INDEX
    Explanations

    world hidden

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hutan
    0.45
    outputPath
    0.44
    森林
    0.43
     forests
    0.43
    ྣ
    0.42
     bosque
    0.41
    ClassObject
    0.40
    다라고
    0.40
     Forests
    0.40
    Forest
    0.39
    POSITIVE LOGITS
    alcohol
    0.44
    。
    0.44
     desperation
    0.41
    oser
    0.41
    pitched
    0.41
     _{(
    0.40
     leash
    0.40
     alcoholism
    0.40
     cost
    0.40
    Від
    0.39
    Act Density 0.057%

    No Known Activations