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

    Neuronpedia

    INDEX
    Explanations

    creation and modification tasks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ى
    0.56
    ïne
    0.54
    WATCH
    0.52
    watch
    0.52
    টি
    0.51
    착
    0.50
    ट
    0.49
    el
    0.48
    있
    0.48
    ів
    0.48
    POSITIVE LOGITS
     tasks
    0.59
     algorithms
    0.56
     Tasks
    0.55
     egli
    0.55
     DIFFIC
    0.55
     abilities
    0.54
     jobSearch
    0.53
     algorit
    0.52
     egreg
    0.52
    🤽
    0.52
    Act Density 0.200%

    No Known Activations