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

    Neuronpedia

    INDEX
    Explanations

    doesn't have to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    localVarPath
    0.77
    StripMenuItem
    0.77
     ট্র্যাক
    0.77
     withstand
    0.76
     valued
    0.75
    accompl
    0.75
     ट्रैक
    0.74
     treated
    0.73
     hebben
    0.73
    堷
    0.73
    POSITIVE LOGITS
    Core
    0.80
     thể
    0.73
    core
    0.73
    ome
    0.71
    no
    0.71
     Core
    0.70
    oci
    0.70
    F
    0.70
    el
    0.68
    voc
    0.67
    Act Density 0.032%

    No Known Activations