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

    Neuronpedia

    INDEX
    Explanations

    explicitly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    াবের
    0.54
     nared
    0.49
    ото
    0.49
     lundi
    0.49
    केर
    0.48
     carbohyd
    0.47
     conseguenza
    0.47
    obtenir
    0.47
    इंग
    0.46
    ωσης
    0.46
    POSITIVE LOGITS
     Bounce
    0.52
    °
    0.50
    áp
    0.49
     Operations
    0.48
     Has
    0.48
     Pá
    0.47
     সম্মিলিত
    0.47
     Beats
    0.47
     Bir
    0.46
     Make
    0.46
    Act Density 0.000%

    No Known Activations