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

    Neuronpedia

    INDEX
    Explanations

    focused on something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    者的
    0.51
    ة
    0.46
    لي
    0.44
    abilità
    0.44
    俦
    0.44
    atge
    0.43
    طي
    0.42
    بة
    0.42
    ні
    0.42
    طان
    0.41
    POSITIVE LOGITS
     archiving
    0.55
     serialization
    0.52
     not
    0.49
     ภาษา
    0.48
     videogame
    0.47
     diocese
    0.47
     compiling
    0.46
     reorganization
    0.46
     bloques
    0.46
    Not
    0.46
    Act Density 0.004%

    No Known Activations