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

    Neuronpedia

    INDEX
    Explanations

    mutation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    범
    0.39
    馕
    0.38
    整備
    0.37
     अनार
    0.37
    ޚ
    0.36
    ]]);
    0.35
    registerTask
    0.35
    间隔
    0.35
    ᖃ
    0.35
     পার্
    0.35
    POSITIVE LOGITS
     mutation
    3.52
    Mut
    3.42
     mutate
    3.38
     Mut
    3.34
     mutations
    3.33
     mut
    3.31
    mut
    3.28
     mutant
    3.27
     mutated
    3.25
     Mutation
    3.25
    Act Density 0.030%

    No Known Activations