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

    Neuronpedia

    INDEX
    Explanations

    names or labels

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cumplen
    0.82
    طاء
    0.77
     cumple
    0.73
     cumplir
    0.72
    godic
    0.71
     कुसुम
    0.66
     страниц
    0.66
    <unused1937>
    0.66
    釦
    0.66
     elkaar
    0.65
    POSITIVE LOGITS
    Jan
    0.71
    Mex
    0.71
     Mex
    0.70
     Con
    0.69
    Rep
    0.68
     Lex
    0.68
     Cl
    0.67
     Mini
    0.66
    PM
    0.66
     Wikiped
    0.66
    Act Density 0.005%

    No Known Activations