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

    Neuronpedia

    INDEX
    Explanations

    "the" followed by `json`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    。.
    0.42
     വന്ന
    0.40
     unus
    0.39
     nowy
    0.38
    Penis
    0.37
     mutton
    0.37
    LowerCase
    0.36
     immer
    0.36
     altid
    0.36
     तम्
    0.36
    POSITIVE LOGITS
     Charitable
    0.34
    篠
    0.33
     stylus
    0.33
    ساعدة
    0.32
     Diversity
    0.32
    க்கழக
    0.32
     Scottish
    0.31
     Andrew
    0.31
     Audio
    0.31
     Tony
    0.30
    Act Density 0.001%

    No Known Activations