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

    Neuronpedia

    INDEX
    Explanations

    particularly, rating, best

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     শক্তি
    0.41
    pit
    0.41
    సక్తి
    0.40
    subseteq
    0.40
    pkins
    0.39
    র্গে
    0.38
     lesbians
    0.37
    udd
    0.37
    cida
    0.37
     बहनों
    0.37
    POSITIVE LOGITS
     Sturm
    0.41
     jellem
    0.39
     Views
    0.37
    いや
    0.37
     kawa
    0.37
    }+
    0.36
     सूर
    0.35
     কাগজে
    0.35
     views
    0.35
    ')),
    0.34
    Act Density 0.000%

    No Known Activations