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

    Neuronpedia

    INDEX
    Explanations

    Declare launch arguments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tad
    0.40
     подви
    0.40
     craftsman
    0.38
     подо
    0.38
     eps
    0.37
    まつ
    0.37
    জ্জ
    0.37
    縞
    0.37
     shaded
    0.36
     आहार
    0.36
    POSITIVE LOGITS
     declarations
    0.54
     Declare
    0.49
     Launch
    0.46
     declaring
    0.46
    composable
    0.45
     declares
    0.45
    Declare
    0.45
    arguments
    0.45
    声明
    0.42
    actions
    0.42
    Act Density 0.000%

    No Known Activations