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

    Neuronpedia

    INDEX
    Explanations

    say *

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Dec
    0.40
    waters
    0.38
    nation
    0.38
     Gonzaga
    0.37
     Sos
    0.37
     pou
    0.37
     Poul
    0.37
     abstract
    0.37
     Pom
    0.36
    राष्ट्र
    0.36
    POSITIVE LOGITS
    Geschichte
    0.38
    NSNumber
    0.36
    чними
    0.36
    Correspond
    0.35
    換
    0.34
    correspond
    0.34
    حي
    0.33
    ိုး
    0.32
    visited
    0.32
    换
    0.32
    Act Density 0.000%

    No Known Activations