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

    Neuronpedia

    INDEX
    Explanations

    technical/scientific texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cigars
    -0.06
    nů
    -0.06
     Pavel
    -0.06
    _singleton
    -0.06
    hidden
    -0.06
                                                    ↵
    -0.06
     borderline
    -0.06
    dataset
    -0.06
     fascist
    -0.06
     oh
    -0.06
    POSITIVE LOGITS
    Gift
    0.07
     Cooking
    0.06
     identifies
    0.06
    ahead
    0.06
    ＋
    0.06
    σχ
    0.06
    أس
    0.06
    +++
    0.06
     energia
    0.06
     Арх
    0.06
    Act Density 0.101%

    No Known Activations