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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions with x

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    A
    0.78
    Construction
    0.77
    PU
    0.75
    ISS
    0.75
    Wi
    0.74
    on
    0.71
    易
    0.70
    Improve
    0.70
    Cop
    0.70
    P
    0.69
    POSITIVE LOGITS
     কোনো
    0.85
     végétaux
    0.85
    ẩm
    0.83
     Eligible
    0.82
     Concentrations
    0.82
    dropDown
    0.81
     wrongful
    0.81
    )_\
    0.81
     descobrir
    0.81
     پرومو
    0.80
    Act Density 0.066%

    No Known Activations