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

    Neuronpedia

    INDEX
    Explanations

    plea or strong appeal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Cors
    0.80
    Cors
    0.75
    굶
    0.72
    btnLogout
    0.71
     bidding
    0.71
     cubes
    0.68
     hostname
    0.68
    Denovo
    0.67
    cors
    0.66
     cube
    0.66
    POSITIVE LOGITS
    FFECT
    0.64
     দেখাতে
    0.63
    ania
    0.60
     بها
    0.60
     attest
    0.55
     सुविधाएं
    0.54
    Fe
    0.53
     effectual
    0.53
     фонда
    0.53
    inity
    0.52
    Act Density 0.150%

    No Known Activations