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

    Neuronpedia

    INDEX
    Explanations

    Hyphen

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     future
    0.54
     two
    0.46
     futuro
    0.46
     ordin
    0.42
     good
    0.41
     ordinary
    0.40
     TWO
    0.39
     Directory
    0.39
     report
    0.38
     будущем
    0.38
    POSITIVE LOGITS
    third
    0.51
    shifts
    0.47
    Third
    0.46
    shift
    0.45
    第三
    0.44
    তৃত
    0.44
    Leet
    0.42
    Characters
    0.42
     Shifts
    0.41
    Shift
    0.41
    Act Density 0.000%

    No Known Activations