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

    Neuronpedia

    INDEX
    Explanations

    regardless, whichever, whatever

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     soms
    0.39
     theoret
    0.38
     apparence
    0.36
     poles
    0.35
     teórico
    0.34
     домаћинствима
    0.34
     иногда
    0.34
     هذا
    0.34
     rohk
    0.34
     fam
    0.33
    POSITIVE LOGITS
     whichever
    2.02
    いずれ
    1.67
     Regardless
    1.58
    Regardless
    1.52
    Whatever
    1.42
     whatever
    1.41
     Whatever
    1.38
     regardless
    1.38
    whatever
    1.32
    ichever
    1.32
    Act Density 0.006%

    No Known Activations