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

    Neuronpedia

    INDEX
    Explanations

    wallstreetbets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    0.65
    KE
    0.64
    4
    0.64
    AL
    0.63
    }
    0.63
    ↵↵
    0.61
    ٤
    0.59
    고
    0.59
     is
    0.58
    ász
    0.58
    POSITIVE LOGITS
    ्स
    0.81
     ambulances
    0.70
    ס
    0.69
    স
    0.68
     było
    0.67
     antigo
    0.66
    स
    0.66
     dinners
    0.65
    Acces
    0.64
     phir
    0.63
    Act Density 0.001%

    No Known Activations