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

    Neuronpedia

    INDEX
    Explanations

    project setup

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dataset
    0.45
     underway
    0.41
     Fund
    0.39
     overseeing
    0.38
    Designs
    0.38
     varsity
    0.38
     asign
    0.38
    atosis
    0.38
     completions
    0.38
     coastline
    0.37
    POSITIVE LOGITS
     جذر
    0.48
     الجذر
    0.48
    根
    0.43
     skeleton
    0.42
     Root
    0.41
    Root
    0.40
     raíz
    0.40
     racines
    0.39
     structure
    0.39
    structure
    0.39
    Act Density 0.006%

    No Known Activations