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

    Neuronpedia

    INDEX
    Explanations

    android appcompat AppCompatActivity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    readValue
    0.47
    สก
    0.39
    丹
    0.37
     ransom
    0.37
     certifications
    0.37
     fwrite
    0.37
    मानस
    0.37
     productService
    0.37
    交流
    0.36
    thag
    0.36
    POSITIVE LOGITS
    appcompat
    1.01
     AppCompat
    0.93
    AppCompat
    0.92
    Compat
    0.68
    Constraint
    0.68
     Compat
    0.64
    constraint
    0.62
     Constraint
    0.59
    compat
    0.56
     constraint
    0.55
    Act Density 0.004%

    No Known Activations