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

    Neuronpedia

    INDEX
    Explanations

    mutable references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ારીખ
    0.40
     непо
    0.40
    Counters
    0.40
    iggle
    0.39
    ável
    0.38
    arza
    0.38
     일이
    0.38
    Mississippi
    0.38
    iflor
    0.37
    ባቸው
    0.37
    POSITIVE LOGITS
    mut
    1.70
     mut
    1.69
     Mut
    1.35
    Mut
    1.31
     mutated
    1.23
     mutant
    1.23
     mutants
    1.17
     MUT
    1.15
     mutate
    1.14
    MUT
    1.12
    Act Density 0.006%

    No Known Activations