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

    Neuronpedia

    INDEX
    Explanations

    unlocks new opportunities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    orthogonal
    0.44
    aldb
    0.44
    EEK
    0.43
    EntityManager
    0.43
     xhrObj
    0.42
    czy
    0.41
    btnAdd
    0.41
    btnUn
    0.41
    jahtera
    0.41
     elevates
    0.41
    POSITIVE LOGITS
     k
    0.50
    t
    0.50
    -
    0.49
     le
    0.47
     pre
    0.47
     к
    0.45
     associated
    0.44
     series
    0.44
     characteristic
    0.44
     उनमें
    0.44
    Act Density 0.000%

    No Known Activations