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

    Neuronpedia

    INDEX
    Explanations

    pygame drawing commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    辇
    0.37
    Climate
    0.36
     Robertson
    0.36
    osome
    0.36
     Zie
    0.36
     Collectors
    0.35
    堷
    0.35
     macrophages
    0.34
    Macrophages
    0.34
    Robertson
    0.34
    POSITIVE LOGITS
     устройств
    0.38
    वार
    0.34
     condizioni
    0.33
     koş
    0.33
     teks
    0.33
     میلیون
    0.33
     सुकून
    0.33
    Colorful
    0.32
     коне
    0.32
    getpath
    0.32
    Act Density 0.003%

    No Known Activations