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

    Neuronpedia

    INDEX
    Explanations

    list item markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     தினமும்
    0.40
     Halloween
    0.38
     अमाउंट
    0.38
     कॉपी
    0.37
     stereotype
    0.37
     ආහාර
    0.37
    ອາຫານ
    0.37
     व्यायाम
    0.36
     загряз
    0.36
     букмекердик
    0.36
    POSITIVE LOGITS
    ↵↵↵
    0.41
    }
    0.36
     and
    0.35
     kalangan
    0.33
    ↵↵
    0.33
      
    0.32
    └──
    0.32
    Cet
    0.32
    .
    0.31
    and
    0.31
    Act Density 0.114%

    No Known Activations