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

    Neuronpedia

    INDEX
    Explanations

    top

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ERR
    -0.08
    נג
    -0.08
    _tipo
    -0.07
    ⬛
    -0.07
    	REQUIRE
    -0.06
     Reb
    -0.06
     masc
    -0.06
     harass
    -0.06
    Il
    -0.06
    蕴含
    -0.06
    POSITIVE LOGITS
     Cake
    0.07
     Causes
    0.07
     Pie
    0.07
    ออ
    0.07
     kal
    0.06
    commit
    0.06
    /bus
    0.06
    /*↵↵
    0.06
     vintage
    0.06
    (show
    0.06
    Act Density 0.001%

    No Known Activations