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

    Neuronpedia

    INDEX
    Explanations

    certain / some languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vreau
    0.57
     Итак
    0.52
     devemos
    0.48
     Поэтому
    0.46
     우리가
    0.46
     allons
    0.45
     ();
    0.45
     komma
    0.45
    Então
    0.44
     మనం
    0.44
    POSITIVE LOGITS
    }
    0.54
    <h2>
    0.50
     ചില
    0.49
    <h3>
    0.49
    ↵↵
    0.49
     criticised
    0.48
    }}
    0.47
     некоторых
    0.47
     certains
    0.46
     برخی
    0.45
    Act Density 0.003%

    No Known Activations