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

    Neuronpedia

    INDEX
    Explanations

    regardless of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     alluded
    0.76
     hinted
    0.73
     ausge
    0.72
     renouvel
    0.70
    ábban
    0.69
     elemento
    0.69
    automne
    0.69
     dispone
    0.69
    漅
    0.69
     confirmed
    0.69
    POSITIVE LOGITS
     unimportant
    2.05
     irrelevant
    1.94
     cares
    1.60
     regardless
    1.55
     matters
    1.55
     mattered
    1.52
    regardless
    1.51
    Regardless
    1.49
     indifferent
    1.47
     Regardless
    1.46
    Act Density 0.314%

    No Known Activations