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

    Neuronpedia

    INDEX
    Explanations

    cloud services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ity
    0.75
    int
    0.75
    inform
    0.72
    show
    0.72
    ain
    0.71
    assign
    0.70
     Warhol
    0.70
    unt
    0.68
    ins
    0.68
    ache
    0.68
    POSITIVE LOGITS
     thoſe
    0.78
    軐
    0.75
    ጆ
    0.75
     APS
    0.73
    counterx
    0.72
    getCQL
    0.72
    entraî
    0.71
    стрі
    0.70
     CTL
    0.69
    Unsupported
    0.69
    Act Density 0.001%

    No Known Activations