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

    Neuronpedia

    INDEX
    Explanations

    verify or confirm

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     moderation
    0.77
    。「
    0.72
    接入
    0.71
     escapes
    0.70
    کو
    0.70
    ຈະ
    0.69
     모르
    0.69
    梅里
    0.69
    catcher
    0.69
    éről
    0.68
    POSITIVE LOGITS
     verify
    0.84
    verify
    0.81
     confirm
    0.80
    Verify
    0.79
     confirmation
    0.78
     Confirm
    0.77
     verifying
    0.75
     verified
    0.74
     Verify
    0.74
     confirming
    0.74
    Act Density 0.027%

    No Known Activations