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

    Neuronpedia

    INDEX
    Explanations

    mutable programming constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     conserver
    0.42
    COLORS
    0.41
    禰
    0.40
    റ്റ
    0.40
     deplete
    0.39
    ioutil
    0.39
     leggere
    0.39
     conserve
    0.38
    தொ
    0.38
     interfere
    0.38
    POSITIVE LOGITS
     Mutable
    0.79
     mutable
    0.79
    Mutable
    0.74
    mutable
    0.69
    Mutability
    0.61
     MUT
    0.56
     Mutation
    0.55
     Mut
    0.55
    mutation
    0.53
    MUT
    0.50
    Act Density 0.008%

    No Known Activations