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

    Neuronpedia

    INDEX
    Explanations

    sentence correction and completion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ఆరోగ్య
    0.42
    bonne
    0.40
     ignoreString
    0.40
     iza
    0.40
    agricult
    0.39
    zingen
    0.39
    idane
    0.39
    pyridazine
    0.38
    stellungen
    0.38
    酝
    0.38
    POSITIVE LOGITS
     general
    0.38
     pse
    0.37
     General
    0.37
     tov
    0.37
     صفحه
    0.36
     berbasis
    0.36
     headquartered
    0.35
    FEED
    0.35
    General
    0.35
     based
    0.34
    Act Density 0.001%

    No Known Activations