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

    Neuronpedia

    INDEX
    Explanations

    manifests or makes appear

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    旖
    0.49
    ри
    0.48
    眽
    0.48
    acly
    0.47
    ärke
    0.47
    є
    0.47
    aremos
    0.46
     će
    0.46
    е
    0.46
    echolog
    0.45
    POSITIVE LOGITS
     manifest
    0.51
     manifeste
    0.46
     magic
    0.45
     libraries
    0.44
     manifests
    0.43
     library
    0.43
     manifestation
    0.43
     manifold
    0.42
     Provider
    0.41
     manifolds
    0.41
    Act Density 0.002%

    No Known Activations