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

    Neuronpedia

    INDEX
    Explanations

    pointers and suggestions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tillman
    0.40
    Truthy
    0.39
    buildSpec
    0.38
    mathspace
    0.38
     stewards
    0.38
    Analyzing
    0.38
    pady
    0.38
    小売
    0.38
     scott
    0.37
     verlie
    0.36
    POSITIVE LOGITS
     指
    0.41
     pointer
    0.41
     gợi
    0.39
     Suggest
    0.38
     compound
    0.38
     sugger
    0.38
     FPGA
    0.37
     pointers
    0.37
     HD
    0.37
     friendship
    0.37
    Act Density 0.000%

    No Known Activations