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

    Neuronpedia

    INDEX
    Explanations

    unauthorised incorrect refunds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     idealized
    0.53
     variabili
    0.48
     formalized
    0.46
     типи
    0.45
     embracing
    0.44
     பெரும்பாலும்
    0.44
     fenómenos
    0.44
     слегка
    0.44
     epigenetic
    0.43
     spannend
    0.43
    POSITIVE LOGITS
     dispute
    0.75
     unauthorised
    0.73
     incorrectly
    0.71
     incorrect
    0.70
     refund
    0.69
     fraudulent
    0.68
     erroneously
    0.68
     refunds
    0.68
     allegedly
    0.67
     disputed
    0.67
    Act Density 0.033%

    No Known Activations