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

    Neuronpedia

    INDEX
    Explanations

    parameter type annotations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ):\
    0.52
     "):
    0.46
     hale
    0.45
    "):
    0.44
    ):=\
    0.42
    )=>{
    0.42
    "?:
    0.41
    }):=\
    0.40
    '):
    0.39
    =")"
    0.38
    POSITIVE LOGITS
     |
    0.56
    |
    0.52
     &&
    0.46
    |}
    0.45
     ||
    0.44
    _|
    0.43
    |$
    0.42
     thereby
    0.42
    &&
    0.41
    }}
    0.41
    Act Density 0.015%

    No Known Activations