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

    Neuronpedia

    INDEX
    Explanations

    Inkscape

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    协
    0.42
    碗
    0.40
     ovens
    0.39
     Cooley
    0.39
     Lagrangian
    0.38
     Horowitz
    0.38
    奻
    0.38
     referral
    0.38
     S
    0.37
     Equals
    0.37
    POSITIVE LOGITS
    ISING
    0.43
     プリント
    0.42
    ള
    0.41
     तिक
    0.39
    Примітки
    0.39
    哩
    0.39
    გუფი
    0.38
    ටි
    0.38
    ন্তা
    0.38
    ASHI
    0.37
    Act Density 0.003%

    No Known Activations