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

    Neuronpedia

    INDEX
    Explanations

    elven

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Serv
    0.71
    ඡ
    0.70
     الخميس
    0.69
    Sat
    0.69
     एक्सच
    0.67
    release
    0.66
    Exp
    0.66
    Cases
    0.65
     इमर
    0.64
    Release
    0.64
    POSITIVE LOGITS
     ven
    0.85
    фи
    0.79
     delicacy
    0.73
    фі
    0.68
    פים
    0.66
     fairy
    0.66
     وف
    0.65
     feta
    0.65
    പ്പ്
    0.64
     venous
    0.64
    Act Density 0.003%

    No Known Activations