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

    Neuronpedia

    INDEX
    Explanations

    unable to create content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Nal
    0.49
     Unterstützung
    0.48
     Unterstüt
    0.47
     Filters
    0.45
    ួយ
    0.44
    uhà
    0.43
     getSupport
    0.43
     Ettha
    0.43
    ánt
    0.43
    горь
    0.43
    POSITIVE LOGITS
     preponderance
    0.44
    om
    0.43
    earing
    0.43
    slag
    0.43
     respectively
    0.42
    orne
    0.42
     clandest
    0.42
     authorizations
    0.42
     determinants
    0.42
     detonations
    0.42
    Act Density 0.000%

    No Known Activations