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

    Neuronpedia

    INDEX
    Explanations

    getters and setters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ު
    0.44
    mime
    0.39
    unistd
    0.38
    soluble
    0.37
     සා
    0.37
    虔
    0.37
    മിതി
    0.37
    人間
    0.37
    綢
    0.37
    mono
    0.36
    POSITIVE LOGITS
     setter
    1.10
     Setter
    1.01
     value
    0.96
    setter
    0.92
     getter
    0.87
     setters
    0.85
    Setter
    0.84
    newValue
    0.79
    getter
    0.77
    value
    0.75
    Act Density 0.011%

    No Known Activations