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

    Neuronpedia

    INDEX
    Explanations

    command-line argument descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     همان
    0.74
    orest
    0.74
    èse
    0.74
     ];
    0.68
     തന്നെ
    0.68
    मंगल
    0.67
    ()];
    0.66
     }));
    0.65
     remarquer
    0.65
     };
    0.65
    POSITIVE LOGITS
     '')
    0.82
    ='')
    0.77
    árias
    0.74
     Load
    0.71
    اصل
    0.69
    หรับ
    0.69
    plicative
    0.68
    ="")
    0.68
     aérea
    0.68
     personalize
    0.68
    Act Density 0.009%

    No Known Activations