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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases and clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    eno
    0.40
    和小
    0.38
     permisos
    0.38
    xin
    0.37
     fume
    0.37
    otipi
    0.37
     அழகு
    0.37
    ষি
    0.36
    ovi
    0.36
    iculos
    0.35
    POSITIVE LOGITS
     jika
    0.50
    ถ้า
    0.48
    🌧
    0.48
    🚨
    0.47
     ஏற்படும்
    0.47
     apabila
    0.47
    會有
    0.46
    ไหล
    0.45
     повлия
    0.45
    หาก
    0.45
    Act Density 0.005%

    No Known Activations