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

    Neuronpedia

    INDEX
    Explanations

    telling or suggesting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     метода
    0.52
     නම්
    0.50
     métodos
    0.48
     স্ক
    0.48
     കീ
    0.48
     afsl
    0.48
     Erde
    0.47
     Slice
    0.47
    ási
    0.47
    Flatten
    0.46
    POSITIVE LOGITS
    ".
    0.52
    t
    0.49
    ;"
    0.46
    ""
    0.46
    "]
    0.44
     pathologies
    0.44
    ":
    0.43
    ".[
    0.43
    {{
    0.43
     neoplasms
    0.43
    Act Density 0.000%

    No Known Activations