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

    Neuronpedia

    INDEX
    Explanations

    font-family: sans-serif

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tahun
    0.88
    Archae
    0.82
     Excav
    0.77
     שנה
    0.71
    Tiempo
    0.70
    Transforms
    0.70
    probable
    0.69
     प्रोटो
    0.68
     NCBI
    0.68
     excavations
    0.66
    POSITIVE LOGITS
     стаў
    0.73
    핳
    0.73
     thirsty
    0.68
     sigh
    0.68
     street
    0.67
    략
    0.67
    zell
    0.66
    껭
    0.66
     př
    0.65
    addContainerGap
    0.65
    Act Density 0.001%

    No Known Activations