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

    Neuronpedia

    INDEX
    Explanations

    assembly language, Python, ADDIE Model

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    λογ
    0.47
     framework
    0.45
     amm
    0.43
     frameworks
    0.43
     clarification
    0.42
    Clar
    0.40
     Framework
    0.40
    Framework
    0.40
     defined
    0.39
     clarifying
    0.39
    POSITIVE LOGITS
     শতাব্দ
    0.42
    ྕ
    0.40
     cicat
    0.40
     shri
    0.39
     orbiting
    0.39
     raven
    0.37
     maniac
    0.37
     sikap
    0.37
    pson
    0.36
    Papers
    0.35
    Act Density 0.008%

    No Known Activations