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

    Neuronpedia

    INDEX
    Explanations

    Deity names and pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     amending
    0.44
     disadvantaged
    0.36
     accounts
    0.35
     Ansprüche
    0.35
    வர்
    0.34
     amendments
    0.33
    гу
    0.33
     sparing
    0.33
     cucumbers
    0.33
     plas
    0.32
    POSITIVE LOGITS
     অথচ
    0.43
    odiac
    0.43
    idać
    0.41
    ieved
    0.40
    ḿ
    0.39
    uate
    0.38
    strated
    0.38
    ние
    0.38
    개월
    0.38
    icitis
    0.38
    Act Density 0.000%

    No Known Activations