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

    Neuronpedia

    INDEX
    Explanations

    Because

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lên
    -0.10
    को
    -0.09
    /down
    -0.08
    song
    -0.08
    playlist
    -0.08
     deductible
    -0.08
     મળે
    -0.08
     मिलता
    -0.08
    (album
    -0.08
    ने
    -0.08
    POSITIVE LOGITS
     ansonsten
    0.09
    Vals
    0.08
     évidemment
    0.08
    これは
    0.08
    _throw
    0.08
     כמובן
    0.08
     presumably
    0.08
     hopefully
    0.08
    assa
    0.07
     паў
    0.07
    Act Density 0.036%

    No Known Activations