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

    Neuronpedia

    INDEX
    Explanations

    header files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ambh
    0.45
    VCTarget
    0.45
    කින්
    0.44
    傊
    0.44
    DOMstrings
    0.44
    㖘
    0.42
     pointillés
    0.42
    @[
    0.42
    舴
    0.42
    恁
    0.41
    POSITIVE LOGITS
     rose
    0.41
    所在的
    0.39
     squ
    0.39
     con
    0.38
     only
    0.38
     potentially
    0.37
    0.37
     Serena
    0.37
    1
    0.37
    td
    0.36
    Act Density 0.000%

    No Known Activations