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

    Neuronpedia

    INDEX
    Explanations

    names with titles or suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     куп
    0.23
    にかけて
    0.23
     זה
    0.22
     onwards
    0.21
     magyar
    0.21
    ടിച്ച
    0.21
    中古
    0.21
    では
    0.21
     அரசா
    0.21
     battleship
    0.21
    POSITIVE LOGITS
     Jr
    0.37
     ওরফে
    0.34
    Jr
    0.32
     PhD
    0.32
     उर्फ
    0.31
    PhD
    0.31
     née
    0.30
     alias
    0.29
    ová
    0.29
     jr
    0.29
    Act Density 0.026%

    No Known Activations