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

    Neuronpedia

    INDEX
    Explanations

    document version

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sauve
    0.73
     savers
    0.71
     aftermath
    0.67
     boobs
    0.66
     amyloid
    0.66
     suffer
    0.66
     just
    0.65
     flux
    0.65
     dend
    0.65
     constraint
    0.65
    POSITIVE LOGITS
    ISBN
    1.09
    Printed
    1.08
    Marketing
    0.94
    Library
    0.93
     Printed
    0.92
    Manufact
    0.91
    Printing
    0.91
     Printing
    0.91
    Logo
    0.88
    Distributed
    0.88
    Act Density 0.000%

    No Known Activations