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

    Neuronpedia

    INDEX
    Explanations

    manifest.json

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    elä
    0.47
    idh
    0.45
    paused
    0.43
    humans
    0.43
    ter
    0.42
    cooled
    0.42
    chips
    0.42
    礪
    0.41
    pmatrix
    0.41
    tery
    0.40
    POSITIVE LOGITS
     manifest
    1.15
     Manifest
    1.02
    Manifest
    1.00
    manifest
    1.00
     manifests
    0.98
     manifesto
    0.96
     manif
    0.89
     manifeste
    0.89
     manifestazione
    0.88
     manifi
    0.87
    Act Density 0.005%

    No Known Activations