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

    Neuronpedia

    INDEX
    Explanations

    rust code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Receptor
    0.48
     cast
    0.43
     CAST
    0.42
     церков
    0.41
     Marr
    0.41
    အခ
    0.40
     Reduction
    0.39
     POLY
    0.38
     लक्ष्मण
    0.38
     Reduced
    0.38
    POSITIVE LOGITS
     println
    0.56
    println
    0.51
     vec
    0.48
    vec
    0.45
    failure
    0.43
    rusty
    0.42
     vector
    0.41
     ownership
    0.41
    executable
    0.41
     failure
    0.41
    Act Density 0.046%

    No Known Activations